Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3836 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2484. Min Range: -6.2484
Max Act: 6.2484. Min Act: -0.1700
Data Index: 1163734 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2484. Min Range: -6.2484
Max Act: 5.8422. Min Act: -0.1700
Data Index: 8026411 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2484. Min Range: -6.2484
Max Act: 5.8109. Min Act: -0.1700
Data Index: 7828724 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2484. Min Range: -6.2484
Max Act: 5.6547. Min Act: -0.1700
Data Index: 4671975 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2484. Min Range: -6.2484
Max Act: 5.6234. Min Act: -0.1700
Data Index: 5733574 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2484. Min Range: -6.2484
Max Act: 5.5922. Min Act: -0.1700
Data Index: 2277805 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2484. Min Range: -6.2484
Max Act: 5.5609. Min Act: -0.1700
Data Index: 7773393 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2484. Min Range: -6.2484
Max Act: 5.5297. Min Act: -0.1700
Data Index: 387501 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2484. Min Range: -6.2484
Max Act: 5.5297. Min Act: -0.1700
Data Index: 3774489 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2484. Min Range: -6.2484
Max Act: 5.5297. Min Act: -0.1700
Data Index: 5925366 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2484. Min Range: -6.2484
Max Act: 5.5297. Min Act: -0.1700
Data Index: 6529460 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2484. Min Range: -6.2484
Max Act: 5.5297. Min Act: -0.1700
Data Index: 5452513 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2484. Min Range: -6.2484
Max Act: 5.4672. Min Act: -0.1700
Data Index: 6672529 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2484. Min Range: -6.2484
Max Act: 5.4672. Min Act: -0.1700
Data Index: 6214738 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2484. Min Range: -6.2484
Max Act: 5.4984. Min Act: -0.1700
Data Index: 946994 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2484. Min Range: -6.2484
Max Act: 5.4672. Min Act: -0.1700
Data Index: 5094171 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2484. Min Range: -6.2484
Max Act: 5.4672. Min Act: -0.1700
Data Index: 6507922 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2484. Min Range: -6.2484
Max Act: 5.4359. Min Act: -0.1700
Data Index: 7895487 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2484. Min Range: -6.2484
Max Act: 5.4359. Min Act: -0.1700
Data Index: 7700537 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2484. Min Range: -6.2484
Max Act: 5.4359. Min Act: -0.1700
Data Index: 3302925 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #19