Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3073 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9602. Min Range: -3.9602
Max Act: 3.9602. Min Act: -0.1700
Data Index: 6720530 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9602. Min Range: -3.9602
Max Act: 3.9289. Min Act: -0.1700
Data Index: 3654176 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9602. Min Range: -3.9602
Max Act: 3.8351. Min Act: -0.1700
Data Index: 4585574 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9602. Min Range: -3.9602
Max Act: 3.7256. Min Act: -0.1700
Data Index: 7355775 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9602. Min Range: -3.9602
Max Act: 3.7256. Min Act: -0.1700
Data Index: 4059463 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9602. Min Range: -3.9602
Max Act: 3.7256. Min Act: -0.1700
Data Index: 1687935 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9602. Min Range: -3.9602
Max Act: 3.7100. Min Act: -0.1700
Data Index: 4233714 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9602. Min Range: -3.9602
Max Act: 3.6787. Min Act: -0.1700
Data Index: 8234768 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9602. Min Range: -3.9602
Max Act: 3.6474. Min Act: -0.1700
Data Index: 748303 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9602. Min Range: -3.9602
Max Act: 3.6318. Min Act: -0.1700
Data Index: 5425890 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9602. Min Range: -3.9602
Max Act: 3.6474. Min Act: -0.1700
Data Index: 8011532 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9602. Min Range: -3.9602
Max Act: 3.6161. Min Act: -0.1700
Data Index: 4282999 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9602. Min Range: -3.9602
Max Act: 3.6005. Min Act: -0.1700
Data Index: 8481144 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9602. Min Range: -3.9602
Max Act: 3.6161. Min Act: -0.1700
Data Index: 7219333 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9602. Min Range: -3.9602
Max Act: 3.6005. Min Act: -0.1700
Data Index: 7056168 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9602. Min Range: -3.9602
Max Act: 3.6005. Min Act: -0.1700
Data Index: 8705887 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9602. Min Range: -3.9602
Max Act: 3.6161. Min Act: -0.1700
Data Index: 3820428 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9602. Min Range: -3.9602
Max Act: 3.5535. Min Act: -0.1700
Data Index: 6069882 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9602. Min Range: -3.9602
Max Act: 3.5378. Min Act: -0.1700
Data Index: 4317239 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9602. Min Range: -3.9602
Max Act: 3.5222. Min Act: -0.1700
Data Index: 4760074 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #19