Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4304 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6998. Min Range: -5.6998
Max Act: 5.6998. Min Act: -0.1700
Data Index: 8388097 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6998. Min Range: -5.6998
Max Act: 5.5748. Min Act: -0.1700
Data Index: 8199923 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6998. Min Range: -5.6998
Max Act: 5.5748. Min Act: -0.1700
Data Index: 1407028 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6998. Min Range: -5.6998
Max Act: 5.5436. Min Act: -0.1700
Data Index: 2491436 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6998. Min Range: -5.6998
Max Act: 5.4498. Min Act: -0.1700
Data Index: 4051002 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6998. Min Range: -5.6998
Max Act: 5.4498. Min Act: -0.1700
Data Index: 7528223 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6998. Min Range: -5.6998
Max Act: 5.3873. Min Act: -0.1700
Data Index: 3597487 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6998. Min Range: -5.6998
Max Act: 5.3561. Min Act: -0.1700
Data Index: 7378878 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6998. Min Range: -5.6998
Max Act: 5.3561. Min Act: -0.1700
Data Index: 4325628 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6998. Min Range: -5.6998
Max Act: 5.3248. Min Act: -0.1700
Data Index: 4617850 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6998. Min Range: -5.6998
Max Act: 5.3248. Min Act: -0.1700
Data Index: 4678655 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6998. Min Range: -5.6998
Max Act: 5.3248. Min Act: -0.1700
Data Index: 4292006 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6998. Min Range: -5.6998
Max Act: 5.2936. Min Act: -0.1700
Data Index: 3334478 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6998. Min Range: -5.6998
Max Act: 5.3248. Min Act: -0.1700
Data Index: 215779 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6998. Min Range: -5.6998
Max Act: 5.3248. Min Act: -0.1700
Data Index: 2864354 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6998. Min Range: -5.6998
Max Act: 5.2936. Min Act: -0.1700
Data Index: 7373851 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6998. Min Range: -5.6998
Max Act: 5.2936. Min Act: -0.1700
Data Index: 2752344 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6998. Min Range: -5.6998
Max Act: 5.2936. Min Act: -0.1700
Data Index: 678667 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6998. Min Range: -5.6998
Max Act: 5.2936. Min Act: -0.1700
Data Index: 292119 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6998. Min Range: -5.6998
Max Act: 5.2936. Min Act: -0.1700
Data Index: 6022975 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #19