Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1743 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0128. Min Range: -4.0128
Max Act: 4.0128. Min Act: -0.1700
Data Index: 5123963 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0128. Min Range: -4.0128
Max Act: 3.7940. Min Act: -0.1700
Data Index: 3168995 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0128. Min Range: -4.0128
Max Act: 3.7314. Min Act: -0.1700
Data Index: 4182414 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0128. Min Range: -4.0128
Max Act: 3.7471. Min Act: -0.1700
Data Index: 5530270 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0128. Min Range: -4.0128
Max Act: 3.7001. Min Act: -0.1700
Data Index: 3888268 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0128. Min Range: -4.0128
Max Act: 3.6845. Min Act: -0.1700
Data Index: 5616646 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0128. Min Range: -4.0128
Max Act: 3.6689. Min Act: -0.1700
Data Index: 2212149 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0128. Min Range: -4.0128
Max Act: 3.6532. Min Act: -0.1700
Data Index: 5697220 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0128. Min Range: -4.0128
Max Act: 3.6532. Min Act: -0.1700
Data Index: 2051338 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0128. Min Range: -4.0128
Max Act: 3.6219. Min Act: -0.1700
Data Index: 8095809 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0128. Min Range: -4.0128
Max Act: 3.6376. Min Act: -0.1700
Data Index: 521786 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0128. Min Range: -4.0128
Max Act: 3.6219. Min Act: -0.1700
Data Index: 3615 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0128. Min Range: -4.0128
Max Act: 3.6063. Min Act: -0.1700
Data Index: 3752029 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0128. Min Range: -4.0128
Max Act: 3.5750. Min Act: -0.1700
Data Index: 2918760 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0128. Min Range: -4.0128
Max Act: 3.5750. Min Act: -0.1700
Data Index: 7830040 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0128. Min Range: -4.0128
Max Act: 3.5750. Min Act: -0.1700
Data Index: 1770887 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0128. Min Range: -4.0128
Max Act: 3.5593. Min Act: -0.1700
Data Index: 4012007 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0128. Min Range: -4.0128
Max Act: 3.5593. Min Act: -0.1700
Data Index: 5692762 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0128. Min Range: -4.0128
Max Act: 3.5593. Min Act: -0.1700
Data Index: 4580479 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0128. Min Range: -4.0128
Max Act: 3.5280. Min Act: -0.1700
Data Index: 8281023 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #19