Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3210 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0384. Min Range: -6.0384
Max Act: 6.0384. Min Act: -0.1700
Data Index: 8705977 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0384. Min Range: -6.0384
Max Act: 5.8821. Min Act: -0.1700
Data Index: 4875139 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0384. Min Range: -6.0384
Max Act: 5.8196. Min Act: -0.1700
Data Index: 8727216 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0384. Min Range: -6.0384
Max Act: 5.8196. Min Act: -0.1700
Data Index: 1727937 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0384. Min Range: -6.0384
Max Act: 5.6946. Min Act: -0.1700
Data Index: 2637573 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0384. Min Range: -6.0384
Max Act: 5.6946. Min Act: -0.1700
Data Index: 2840128 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0384. Min Range: -6.0384
Max Act: 5.6946. Min Act: -0.1700
Data Index: 4133850 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0384. Min Range: -6.0384
Max Act: 5.6634. Min Act: -0.1700
Data Index: 72768 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0384. Min Range: -6.0384
Max Act: 5.6321. Min Act: -0.1700
Data Index: 7565079 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0384. Min Range: -6.0384
Max Act: 5.6009. Min Act: -0.1700
Data Index: 7675005 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0384. Min Range: -6.0384
Max Act: 5.6009. Min Act: -0.1700
Data Index: 5740517 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0384. Min Range: -6.0384
Max Act: 5.5696. Min Act: -0.1700
Data Index: 1787977 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0384. Min Range: -6.0384
Max Act: 5.5696. Min Act: -0.1700
Data Index: 8723595 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0384. Min Range: -6.0384
Max Act: 5.5071. Min Act: -0.1700
Data Index: 2020267 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0384. Min Range: -6.0384
Max Act: 5.4759. Min Act: -0.1700
Data Index: 6699772 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0384. Min Range: -6.0384
Max Act: 5.4759. Min Act: -0.1700
Data Index: 2333951 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0384. Min Range: -6.0384
Max Act: 5.4446. Min Act: -0.1700
Data Index: 8055601 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0384. Min Range: -6.0384
Max Act: 5.4446. Min Act: -0.1698
Data Index: 1946793 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0384. Min Range: -6.0384
Max Act: 5.4446. Min Act: -0.1700
Data Index: 362959 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0384. Min Range: -6.0384
Max Act: 5.4134. Min Act: -0.1700
Data Index: 3068016 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #19