Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3041 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3038. Min Range: -5.3038
Max Act: 5.3038. Min Act: -0.1700
Data Index: 6250233 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3038. Min Range: -5.3038
Max Act: 5.1788. Min Act: -0.1700
Data Index: 7415322 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3038. Min Range: -5.3038
Max Act: 5.1788. Min Act: -0.1700
Data Index: 8166699 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3038. Min Range: -5.3038
Max Act: 5.1476. Min Act: -0.1700
Data Index: 6250234 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3038. Min Range: -5.3038
Max Act: 5.1476. Min Act: -0.1700
Data Index: 1308271 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3038. Min Range: -5.3038
Max Act: 5.1476. Min Act: -0.1700
Data Index: 2174469 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3038. Min Range: -5.3038
Max Act: 5.1476. Min Act: -0.1700
Data Index: 5733855 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3038. Min Range: -5.3038
Max Act: 5.0851. Min Act: -0.1700
Data Index: 2045044 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3038. Min Range: -5.3038
Max Act: 5.0851. Min Act: -0.1700
Data Index: 1192448 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3038. Min Range: -5.3038
Max Act: 5.0851. Min Act: -0.1700
Data Index: 8520035 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3038. Min Range: -5.3038
Max Act: 5.0851. Min Act: -0.1700
Data Index: 3021069 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3038. Min Range: -5.3038
Max Act: 5.0851. Min Act: -0.1700
Data Index: 6268096 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3038. Min Range: -5.3038
Max Act: 5.1163. Min Act: -0.1700
Data Index: 787743 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3038. Min Range: -5.3038
Max Act: 5.0538. Min Act: -0.1700
Data Index: 3539992 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3038. Min Range: -5.3038
Max Act: 5.0226. Min Act: -0.1700
Data Index: 4120661 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3038. Min Range: -5.3038
Max Act: 5.0851. Min Act: -0.1700
Data Index: 8412062 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3038. Min Range: -5.3038
Max Act: 5.0538. Min Act: -0.1700
Data Index: 2454958 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3038. Min Range: -5.3038
Max Act: 5.0226. Min Act: -0.1700
Data Index: 104512 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3038. Min Range: -5.3038
Max Act: 4.9913. Min Act: -0.1700
Data Index: 2350587 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3038. Min Range: -5.3038
Max Act: 5.0226. Min Act: -0.1700
Data Index: 6633420 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #19