Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3338 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6488. Min Range: -4.6488
Max Act: 4.6488. Min Act: -0.1700
Data Index: 1760511 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6488. Min Range: -4.6488
Max Act: 4.3988. Min Act: -0.1700
Data Index: 2071970 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6488. Min Range: -4.6488
Max Act: 4.3363. Min Act: -0.1700
Data Index: 7196327 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6488. Min Range: -4.6488
Max Act: 4.3363. Min Act: -0.1700
Data Index: 3016829 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6488. Min Range: -4.6488
Max Act: 4.3363. Min Act: -0.1700
Data Index: 6345612 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6488. Min Range: -4.6488
Max Act: 4.2738. Min Act: -0.1700
Data Index: 4431057 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6488. Min Range: -4.6488
Max Act: 4.2426. Min Act: -0.1700
Data Index: 730599 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6488. Min Range: -4.6488
Max Act: 4.2426. Min Act: -0.1700
Data Index: 5969879 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6488. Min Range: -4.6488
Max Act: 4.2426. Min Act: -0.1700
Data Index: 8216313 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6488. Min Range: -4.6488
Max Act: 4.2426. Min Act: -0.1700
Data Index: 6048705 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6488. Min Range: -4.6488
Max Act: 4.2426. Min Act: -0.1700
Data Index: 2894237 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6488. Min Range: -4.6488
Max Act: 4.2113. Min Act: -0.1700
Data Index: 7937413 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6488. Min Range: -4.6488
Max Act: 4.2113. Min Act: -0.1700
Data Index: 7377881 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6488. Min Range: -4.6488
Max Act: 4.2113. Min Act: -0.1700
Data Index: 6345617 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6488. Min Range: -4.6488
Max Act: 4.2113. Min Act: -0.1700
Data Index: 6010463 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6488. Min Range: -4.6488
Max Act: 4.1801. Min Act: -0.1700
Data Index: 7937415 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6488. Min Range: -4.6488
Max Act: 4.2113. Min Act: -0.1700
Data Index: 4431056 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6488. Min Range: -4.6488
Max Act: 4.1801. Min Act: -0.1700
Data Index: 730600 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6488. Min Range: -4.6488
Max Act: 4.1488. Min Act: -0.1700
Data Index: 6345616 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6488. Min Range: -4.6488
Max Act: 4.1488. Min Act: -0.1700
Data Index: 2506035 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #19