Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4734 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8910. Min Range: -5.8910
Max Act: 5.8910. Min Act: -0.1700
Data Index: 707780 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8910. Min Range: -5.8910
Max Act: 5.7660. Min Act: -0.1700
Data Index: 3068545 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8910. Min Range: -5.8910
Max Act: 5.4535. Min Act: -0.1700
Data Index: 2040672 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8910. Min Range: -5.8910
Max Act: 5.4847. Min Act: -0.1700
Data Index: 7649289 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8910. Min Range: -5.8910
Max Act: 5.4222. Min Act: -0.1700
Data Index: 845989 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8910. Min Range: -5.8910
Max Act: 5.4222. Min Act: -0.1700
Data Index: 2067123 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8910. Min Range: -5.8910
Max Act: 5.3910. Min Act: -0.1700
Data Index: 1698613 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8910. Min Range: -5.8910
Max Act: 5.3597. Min Act: -0.1700
Data Index: 4054826 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8910. Min Range: -5.8910
Max Act: 5.3597. Min Act: -0.1700
Data Index: 3469524 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8910. Min Range: -5.8910
Max Act: 5.3597. Min Act: -0.1700
Data Index: 4459230 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8910. Min Range: -5.8910
Max Act: 5.3285. Min Act: -0.1700
Data Index: 7789092 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8910. Min Range: -5.8910
Max Act: 5.3285. Min Act: -0.1700
Data Index: 8105866 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8910. Min Range: -5.8910
Max Act: 5.2972. Min Act: -0.1700
Data Index: 1507832 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8910. Min Range: -5.8910
Max Act: 5.2972. Min Act: -0.1700
Data Index: 7426553 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8910. Min Range: -5.8910
Max Act: 5.2972. Min Act: -0.1700
Data Index: 5255531 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8910. Min Range: -5.8910
Max Act: 5.2972. Min Act: -0.1700
Data Index: 2155432 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8910. Min Range: -5.8910
Max Act: 5.2972. Min Act: -0.1700
Data Index: 5429302 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8910. Min Range: -5.8910
Max Act: 5.2972. Min Act: -0.1700
Data Index: 1006448 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8910. Min Range: -5.8910
Max Act: 5.2972. Min Act: -0.1700
Data Index: 6897424 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8910. Min Range: -5.8910
Max Act: 5.2972. Min Act: -0.1700
Data Index: 4805446 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #19