Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4866 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0422. Min Range: -7.0422
Max Act: 7.0422. Min Act: -0.1700
Data Index: 6156594 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0422. Min Range: -7.0422
Max Act: 6.9172. Min Act: -0.1700
Data Index: 571731 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0422. Min Range: -7.0422
Max Act: 6.9172. Min Act: -0.1700
Data Index: 6034386 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0422. Min Range: -7.0422
Max Act: 6.8860. Min Act: -0.1700
Data Index: 7999554 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0422. Min Range: -7.0422
Max Act: 6.8547. Min Act: -0.1700
Data Index: 3247050 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0422. Min Range: -7.0422
Max Act: 6.8235. Min Act: -0.1700
Data Index: 140494 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0422. Min Range: -7.0422
Max Act: 6.7922. Min Act: -0.1700
Data Index: 1233227 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0422. Min Range: -7.0422
Max Act: 6.7610. Min Act: -0.1700
Data Index: 4760432 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0422. Min Range: -7.0422
Max Act: 6.7297. Min Act: -0.1700
Data Index: 3077177 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0422. Min Range: -7.0422
Max Act: 6.7610. Min Act: -0.1700
Data Index: 768289 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0422. Min Range: -7.0422
Max Act: 6.7610. Min Act: -0.1700
Data Index: 5776933 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0422. Min Range: -7.0422
Max Act: 6.7297. Min Act: -0.1700
Data Index: 1496413 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0422. Min Range: -7.0422
Max Act: 6.6985. Min Act: -0.1700
Data Index: 5672582 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0422. Min Range: -7.0422
Max Act: 6.6985. Min Act: -0.1700
Data Index: 4814447 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0422. Min Range: -7.0422
Max Act: 6.6985. Min Act: -0.1700
Data Index: 3952557 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0422. Min Range: -7.0422
Max Act: 6.7297. Min Act: -0.1700
Data Index: 1866768 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0422. Min Range: -7.0422
Max Act: 6.6672. Min Act: -0.1700
Data Index: 862482 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0422. Min Range: -7.0422
Max Act: 6.6672. Min Act: -0.1700
Data Index: 6084812 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0422. Min Range: -7.0422
Max Act: 6.6672. Min Act: -0.1700
Data Index: 3842187 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0422. Min Range: -7.0422
Max Act: 6.6672. Min Act: -0.1700
Data Index: 1932828 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #19