Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2537 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.0005. Min Range: -10.0005
Max Act: 10.0005. Min Act: -0.1700
Data Index: 8661468 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.0005. Min Range: -10.0005
Max Act: 9.6255. Min Act: -0.1700
Data Index: 3922134 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.0005. Min Range: -10.0005
Max Act: 9.4380. Min Act: -0.1700
Data Index: 5422785 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.0005. Min Range: -10.0005
Max Act: 9.4380. Min Act: -0.1700
Data Index: 1983334 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.0005. Min Range: -10.0005
Max Act: 9.3130. Min Act: -0.1700
Data Index: 1910045 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.0005. Min Range: -10.0005
Max Act: 9.3130. Min Act: -0.1700
Data Index: 6406488 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.0005. Min Range: -10.0005
Max Act: 9.2505. Min Act: -0.1700
Data Index: 554085 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.0005. Min Range: -10.0005
Max Act: 9.2505. Min Act: -0.1700
Data Index: 5179973 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.0005. Min Range: -10.0005
Max Act: 9.1880. Min Act: -0.1700
Data Index: 3695377 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.0005. Min Range: -10.0005
Max Act: 9.1880. Min Act: -0.1700
Data Index: 1868478 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.0005. Min Range: -10.0005
Max Act: 9.1255. Min Act: -0.1700
Data Index: 1607993 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.0005. Min Range: -10.0005
Max Act: 9.0630. Min Act: -0.1700
Data Index: 613839 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.0005. Min Range: -10.0005
Max Act: 9.1255. Min Act: -0.1700
Data Index: 2038600 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.0005. Min Range: -10.0005
Max Act: 9.0630. Min Act: -0.1700
Data Index: 4388602 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.0005. Min Range: -10.0005
Max Act: 9.0005. Min Act: -0.1700
Data Index: 6295708 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.0005. Min Range: -10.0005
Max Act: 9.0005. Min Act: -0.1700
Data Index: 4791534 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.0005. Min Range: -10.0005
Max Act: 9.0005. Min Act: -0.1700
Data Index: 4876310 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.0005. Min Range: -10.0005
Max Act: 9.0005. Min Act: -0.1700
Data Index: 6958707 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.0005. Min Range: -10.0005
Max Act: 9.0005. Min Act: -0.1700
Data Index: 4796063 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.0005. Min Range: -10.0005
Max Act: 9.0005. Min Act: -0.1700
Data Index: 5628727 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #19