Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5353 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0598. Min Range: -7.0598
Max Act: 7.0598. Min Act: -0.1700
Data Index: 7715519 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0598. Min Range: -7.0598
Max Act: 7.0285. Min Act: -0.1700
Data Index: 3826289 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0598. Min Range: -7.0598
Max Act: 6.9348. Min Act: -0.1700
Data Index: 980981 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0598. Min Range: -7.0598
Max Act: 6.9035. Min Act: -0.1700
Data Index: 4234183 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0598. Min Range: -7.0598
Max Act: 6.8098. Min Act: -0.1700
Data Index: 7452750 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0598. Min Range: -7.0598
Max Act: 6.7473. Min Act: -0.1700
Data Index: 8718432 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0598. Min Range: -7.0598
Max Act: 6.7473. Min Act: -0.1700
Data Index: 7026567 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0598. Min Range: -7.0598
Max Act: 6.7160. Min Act: -0.1700
Data Index: 5583428 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0598. Min Range: -7.0598
Max Act: 6.6535. Min Act: -0.1700
Data Index: 4784651 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0598. Min Range: -7.0598
Max Act: 6.5910. Min Act: -0.1700
Data Index: 8575640 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0598. Min Range: -7.0598
Max Act: 6.5910. Min Act: -0.1700
Data Index: 3534216 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0598. Min Range: -7.0598
Max Act: 6.5598. Min Act: -0.1700
Data Index: 2807246 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0598. Min Range: -7.0598
Max Act: 6.5598. Min Act: -0.1700
Data Index: 6613489 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0598. Min Range: -7.0598
Max Act: 6.5285. Min Act: -0.1700
Data Index: 8572714 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0598. Min Range: -7.0598
Max Act: 6.4660. Min Act: -0.1700
Data Index: 5029244 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0598. Min Range: -7.0598
Max Act: 6.4660. Min Act: -0.1700
Data Index: 3710450 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0598. Min Range: -7.0598
Max Act: 6.4348. Min Act: -0.1700
Data Index: 4878546 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0598. Min Range: -7.0598
Max Act: 6.4660. Min Act: -0.1700
Data Index: 6263964 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0598. Min Range: -7.0598
Max Act: 6.4660. Min Act: -0.1700
Data Index: 4169961 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0598. Min Range: -7.0598
Max Act: 6.4348. Min Act: -0.1700
Data Index: 636004 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #19