Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4220 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0147. Min Range: -4.0147
Max Act: 4.0147. Min Act: -0.1700
Data Index: 419805 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0147. Min Range: -4.0147
Max Act: 3.9834. Min Act: -0.1700
Data Index: 6919354 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0147. Min Range: -4.0147
Max Act: 3.9522. Min Act: -0.1700
Data Index: 4844675 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0147. Min Range: -4.0147
Max Act: 3.8896. Min Act: -0.1700
Data Index: 7544387 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0147. Min Range: -4.0147
Max Act: 3.8896. Min Act: -0.1700
Data Index: 799721 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0147. Min Range: -4.0147
Max Act: 3.8584. Min Act: -0.1700
Data Index: 733777 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0147. Min Range: -4.0147
Max Act: 3.8584. Min Act: -0.1700
Data Index: 1140921 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0147. Min Range: -4.0147
Max Act: 3.8584. Min Act: -0.1700
Data Index: 4531213 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0147. Min Range: -4.0147
Max Act: 3.8584. Min Act: -0.1700
Data Index: 7770802 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0147. Min Range: -4.0147
Max Act: 3.8584. Min Act: -0.1700
Data Index: 3174478 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0147. Min Range: -4.0147
Max Act: 3.8271. Min Act: -0.1700
Data Index: 999723 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0147. Min Range: -4.0147
Max Act: 3.8584. Min Act: -0.1700
Data Index: 5590009 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0147. Min Range: -4.0147
Max Act: 3.8271. Min Act: -0.1700
Data Index: 8438216 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0147. Min Range: -4.0147
Max Act: 3.7958. Min Act: -0.1700
Data Index: 645164 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0147. Min Range: -4.0147
Max Act: 3.8271. Min Act: -0.1700
Data Index: 7168450 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0147. Min Range: -4.0147
Max Act: 3.7958. Min Act: -0.1700
Data Index: 6741388 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0147. Min Range: -4.0147
Max Act: 3.7958. Min Act: -0.1700
Data Index: 5702623 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0147. Min Range: -4.0147
Max Act: 3.7645. Min Act: -0.1700
Data Index: 4223771 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0147. Min Range: -4.0147
Max Act: 3.7645. Min Act: -0.1700
Data Index: 535271 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0147. Min Range: -4.0147
Max Act: 3.7645. Min Act: -0.1700
Data Index: 3736205 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #19