Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3534 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9152. Min Range: -5.9152
Max Act: 5.9152. Min Act: -0.1700
Data Index: 2289629 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9152. Min Range: -5.9152
Max Act: 5.8527. Min Act: -0.1700
Data Index: 3251113 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9152. Min Range: -5.9152
Max Act: 5.8527. Min Act: -0.1700
Data Index: 8623620 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9152. Min Range: -5.9152
Max Act: 5.8215. Min Act: -0.1700
Data Index: 3084788 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9152. Min Range: -5.9152
Max Act: 5.7590. Min Act: -0.1700
Data Index: 8676429 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9152. Min Range: -5.9152
Max Act: 5.7590. Min Act: -0.1700
Data Index: 2316122 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9152. Min Range: -5.9152
Max Act: 5.7590. Min Act: -0.1700
Data Index: 3556650 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9152. Min Range: -5.9152
Max Act: 5.7277. Min Act: -0.1700
Data Index: 38350 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9152. Min Range: -5.9152
Max Act: 5.7590. Min Act: -0.1700
Data Index: 4044584 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9152. Min Range: -5.9152
Max Act: 5.7277. Min Act: -0.1700
Data Index: 5947172 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9152. Min Range: -5.9152
Max Act: 5.6965. Min Act: -0.1700
Data Index: 8164082 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9152. Min Range: -5.9152
Max Act: 5.6965. Min Act: -0.1700
Data Index: 1984091 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9152. Min Range: -5.9152
Max Act: 5.6965. Min Act: -0.1700
Data Index: 6991535 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9152. Min Range: -5.9152
Max Act: 5.6652. Min Act: -0.1700
Data Index: 1176604 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9152. Min Range: -5.9152
Max Act: 5.6652. Min Act: -0.1700
Data Index: 5180862 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9152. Min Range: -5.9152
Max Act: 5.6340. Min Act: -0.1700
Data Index: 6367300 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9152. Min Range: -5.9152
Max Act: 5.6340. Min Act: -0.1700
Data Index: 7837127 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9152. Min Range: -5.9152
Max Act: 5.6027. Min Act: -0.1700
Data Index: 7837132 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9152. Min Range: -5.9152
Max Act: 5.6340. Min Act: -0.1700
Data Index: 5851823 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9152. Min Range: -5.9152
Max Act: 5.6027. Min Act: -0.1700
Data Index: 6723038 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #19