Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4108 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 11.6999. Min Range: -11.6999
Max Act: 11.6999. Min Act: -0.1700
Data Index: 8382098 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.6999. Min Range: -11.6999
Max Act: 11.5749. Min Act: -0.1700
Data Index: 3338675 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.6999. Min Range: -11.6999
Max Act: 11.5124. Min Act: -0.1700
Data Index: 6813351 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.6999. Min Range: -11.6999
Max Act: 11.4499. Min Act: -0.1700
Data Index: 6053477 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.6999. Min Range: -11.6999
Max Act: 11.3874. Min Act: -0.1700
Data Index: 522468 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.6999. Min Range: -11.6999
Max Act: 11.3874. Min Act: -0.1700
Data Index: 4288142 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.6999. Min Range: -11.6999
Max Act: 11.3874. Min Act: -0.1700
Data Index: 1965331 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.6999. Min Range: -11.6999
Max Act: 11.3249. Min Act: -0.1700
Data Index: 5109628 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.6999. Min Range: -11.6999
Max Act: 11.2624. Min Act: -0.1700
Data Index: 7924076 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.6999. Min Range: -11.6999
Max Act: 11.2624. Min Act: -0.1700
Data Index: 5576589 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.6999. Min Range: -11.6999
Max Act: 11.1999. Min Act: -0.1700
Data Index: 7316633 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.6999. Min Range: -11.6999
Max Act: 11.0749. Min Act: -0.1700
Data Index: 4564789 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.6999. Min Range: -11.6999
Max Act: 11.0124. Min Act: -0.1700
Data Index: 4278573 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.6999. Min Range: -11.6999
Max Act: 11.0124. Min Act: -0.1700
Data Index: 5363970 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.6999. Min Range: -11.6999
Max Act: 11.0124. Min Act: -0.1700
Data Index: 3070939 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.6999. Min Range: -11.6999
Max Act: 10.9499. Min Act: -0.1700
Data Index: 5835086 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.6999. Min Range: -11.6999
Max Act: 10.9499. Min Act: -0.1700
Data Index: 2285341 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.6999. Min Range: -11.6999
Max Act: 10.8874. Min Act: -0.1700
Data Index: 2204237 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.6999. Min Range: -11.6999
Max Act: 10.8874. Min Act: -0.1700
Data Index: 4746410 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.6999. Min Range: -11.6999
Max Act: 10.8874. Min Act: -0.1700
Data Index: 1745093 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #19