Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5704 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 14.8842. Min Range: -14.8842
Max Act: 14.8842. Min Act: -0.1700
Data Index: 2224224 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 14.8842. Min Range: -14.8842
Max Act: 14.7592. Min Act: -0.1700
Data Index: 3324088 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 14.8842. Min Range: -14.8842
Max Act: 14.7592. Min Act: -0.1700
Data Index: 8742424 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 14.8842. Min Range: -14.8842
Max Act: 14.4467. Min Act: -0.1700
Data Index: 7123637 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 14.8842. Min Range: -14.8842
Max Act: 14.3842. Min Act: -0.1700
Data Index: 1290628 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 14.8842. Min Range: -14.8842
Max Act: 14.3842. Min Act: -0.1700
Data Index: 2498674 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 14.8842. Min Range: -14.8842
Max Act: 14.3842. Min Act: -0.1700
Data Index: 3106419 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 14.8842. Min Range: -14.8842
Max Act: 14.3217. Min Act: -0.1700
Data Index: 7961191 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 14.8842. Min Range: -14.8842
Max Act: 14.3217. Min Act: -0.1700
Data Index: 1954732 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 14.8842. Min Range: -14.8842
Max Act: 14.2592. Min Act: -0.1700
Data Index: 7294275 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 14.8842. Min Range: -14.8842
Max Act: 14.2592. Min Act: -0.1700
Data Index: 5144068 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 14.8842. Min Range: -14.8842
Max Act: 14.1967. Min Act: -0.1700
Data Index: 3681981 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 14.8842. Min Range: -14.8842
Max Act: 14.1967. Min Act: -0.1700
Data Index: 4056968 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 14.8842. Min Range: -14.8842
Max Act: 14.2592. Min Act: -0.1700
Data Index: 3790477 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 14.8842. Min Range: -14.8842
Max Act: 14.1967. Min Act: -0.1700
Data Index: 1559970 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 14.8842. Min Range: -14.8842
Max Act: 14.1967. Min Act: -0.1700
Data Index: 2432418 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 14.8842. Min Range: -14.8842
Max Act: 14.1342. Min Act: -0.1700
Data Index: 7563452 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 14.8842. Min Range: -14.8842
Max Act: 14.1342. Min Act: -0.1700
Data Index: 6671392 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 14.8842. Min Range: -14.8842
Max Act: 14.1342. Min Act: -0.1700
Data Index: 4189707 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 14.8842. Min Range: -14.8842
Max Act: 14.1342. Min Act: -0.1700
Data Index: 2333041 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #19