Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4008 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4259. Min Range: -5.4259
Max Act: 5.4259. Min Act: -0.1700
Data Index: 8179333 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4259. Min Range: -5.4259
Max Act: 5.3321. Min Act: -0.1700
Data Index: 8809192 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4259. Min Range: -5.4259
Max Act: 5.2384. Min Act: -0.1700
Data Index: 6538747 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4259. Min Range: -5.4259
Max Act: 5.1446. Min Act: -0.1700
Data Index: 4977381 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4259. Min Range: -5.4259
Max Act: 5.1446. Min Act: -0.1700
Data Index: 7392603 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4259. Min Range: -5.4259
Max Act: 5.1134. Min Act: -0.1700
Data Index: 5446090 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4259. Min Range: -5.4259
Max Act: 5.0821. Min Act: -0.1700
Data Index: 4944415 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4259. Min Range: -5.4259
Max Act: 5.0821. Min Act: -0.1700
Data Index: 3163441 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4259. Min Range: -5.4259
Max Act: 5.0821. Min Act: -0.1700
Data Index: 2264551 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4259. Min Range: -5.4259
Max Act: 5.0821. Min Act: -0.1700
Data Index: 24611 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4259. Min Range: -5.4259
Max Act: 5.0509. Min Act: -0.1700
Data Index: 748902 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4259. Min Range: -5.4259
Max Act: 5.0509. Min Act: -0.1700
Data Index: 1573101 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4259. Min Range: -5.4259
Max Act: 4.9884. Min Act: -0.1700
Data Index: 3049594 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4259. Min Range: -5.4259
Max Act: 4.9571. Min Act: -0.1700
Data Index: 2017082 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4259. Min Range: -5.4259
Max Act: 4.9571. Min Act: -0.1700
Data Index: 5046999 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4259. Min Range: -5.4259
Max Act: 4.9571. Min Act: -0.1700
Data Index: 6960864 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4259. Min Range: -5.4259
Max Act: 4.9571. Min Act: -0.1700
Data Index: 5575447 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4259. Min Range: -5.4259
Max Act: 4.9259. Min Act: -0.1700
Data Index: 4845020 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4259. Min Range: -5.4259
Max Act: 4.9259. Min Act: -0.1700
Data Index: 576655 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4259. Min Range: -5.4259
Max Act: 4.9259. Min Act: -0.1700
Data Index: 5172447 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #19