Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3277 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8011. Min Range: -5.8011
Max Act: 5.8011. Min Act: -0.1700
Data Index: 2208359 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8011. Min Range: -5.8011
Max Act: 5.6761. Min Act: -0.1700
Data Index: 5966761 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8011. Min Range: -5.8011
Max Act: 5.6761. Min Act: -0.1700
Data Index: 5531020 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8011. Min Range: -5.8011
Max Act: 5.6136. Min Act: -0.1700
Data Index: 2303734 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8011. Min Range: -5.8011
Max Act: 5.6136. Min Act: -0.1700
Data Index: 8233248 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8011. Min Range: -5.8011
Max Act: 5.6136. Min Act: -0.1700
Data Index: 2277563 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8011. Min Range: -5.8011
Max Act: 5.6448. Min Act: -0.1700
Data Index: 3529473 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8011. Min Range: -5.8011
Max Act: 5.5823. Min Act: -0.1700
Data Index: 2845392 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8011. Min Range: -5.8011
Max Act: 5.5511. Min Act: -0.1700
Data Index: 5300376 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8011. Min Range: -5.8011
Max Act: 5.5198. Min Act: -0.1700
Data Index: 842209 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8011. Min Range: -5.8011
Max Act: 5.5511. Min Act: -0.1700
Data Index: 6326040 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8011. Min Range: -5.8011
Max Act: 5.5198. Min Act: -0.1700
Data Index: 779422 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8011. Min Range: -5.8011
Max Act: 5.4886. Min Act: -0.1700
Data Index: 7000726 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8011. Min Range: -5.8011
Max Act: 5.4573. Min Act: -0.1700
Data Index: 8208427 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8011. Min Range: -5.8011
Max Act: 5.4573. Min Act: -0.1700
Data Index: 5046084 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8011. Min Range: -5.8011
Max Act: 5.4573. Min Act: -0.1700
Data Index: 2958505 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8011. Min Range: -5.8011
Max Act: 5.4261. Min Act: -0.1700
Data Index: 154059 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8011. Min Range: -5.8011
Max Act: 5.3948. Min Act: -0.1700
Data Index: 5358037 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8011. Min Range: -5.8011
Max Act: 5.4261. Min Act: -0.1700
Data Index: 3139082 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8011. Min Range: -5.8011
Max Act: 5.4261. Min Act: -0.1700
Data Index: 142213 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #19