Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 517 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.2432. Min Range: -3.2432
Max Act: 3.2432. Min Act: -0.1700
Data Index: 3425963 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2432. Min Range: -3.2432
Max Act: 3.2118. Min Act: -0.1700
Data Index: 3824207 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2432. Min Range: -3.2432
Max Act: 3.1646. Min Act: -0.1700
Data Index: 3425968 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2432. Min Range: -3.2432
Max Act: 3.1646. Min Act: -0.1700
Data Index: 3425976 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2432. Min Range: -3.2432
Max Act: 3.1331. Min Act: -0.1700
Data Index: 1402829 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2432. Min Range: -3.2432
Max Act: 3.1174. Min Act: -0.1700
Data Index: 3425965 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2432. Min Range: -3.2432
Max Act: 3.1174. Min Act: -0.1700
Data Index: 7572402 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2432. Min Range: -3.2432
Max Act: 3.1016. Min Act: -0.1700
Data Index: 8345222 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2432. Min Range: -3.2432
Max Act: 3.1016. Min Act: -0.1700
Data Index: 7572407 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2432. Min Range: -3.2432
Max Act: 3.0858. Min Act: -0.1700
Data Index: 5554167 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2432. Min Range: -3.2432
Max Act: 3.1016. Min Act: -0.1700
Data Index: 7572405 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2432. Min Range: -3.2432
Max Act: 3.0701. Min Act: -0.1700
Data Index: 1402828 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2432. Min Range: -3.2432
Max Act: 3.0543. Min Act: -0.1700
Data Index: 6484898 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2432. Min Range: -3.2432
Max Act: 3.0543. Min Act: -0.1700
Data Index: 6361538 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2432. Min Range: -3.2432
Max Act: 3.0543. Min Act: -0.1700
Data Index: 3425967 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2432. Min Range: -3.2432
Max Act: 3.0385. Min Act: -0.1700
Data Index: 2525150 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2432. Min Range: -3.2432
Max Act: 3.0385. Min Act: -0.1700
Data Index: 3369068 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2432. Min Range: -3.2432
Max Act: 3.0543. Min Act: -0.1700
Data Index: 6392115 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2432. Min Range: -3.2432
Max Act: 3.0543. Min Act: -0.1700
Data Index: 3425966 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2432. Min Range: -3.2432
Max Act: 3.0385. Min Act: -0.1700
Data Index: 237828 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #19