Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 223 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.1908. Min Range: -9.1908
Max Act: 9.1908. Min Act: -0.1700
Data Index: 7356406 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.1908. Min Range: -9.1908
Max Act: 8.8158. Min Act: -0.1700
Data Index: 1740631 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.1908. Min Range: -9.1908
Max Act: 8.7533. Min Act: -0.1700
Data Index: 3857506 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.1908. Min Range: -9.1908
Max Act: 8.6908. Min Act: -0.1700
Data Index: 5586006 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.1908. Min Range: -9.1908
Max Act: 8.6908. Min Act: -0.1700
Data Index: 6309969 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.1908. Min Range: -9.1908
Max Act: 8.6908. Min Act: -0.1700
Data Index: 7773278 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.1908. Min Range: -9.1908
Max Act: 8.6908. Min Act: -0.1700
Data Index: 416455 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.1908. Min Range: -9.1908
Max Act: 8.6283. Min Act: -0.1700
Data Index: 564456 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.1908. Min Range: -9.1908
Max Act: 8.5033. Min Act: -0.1700
Data Index: 8218745 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.1908. Min Range: -9.1908
Max Act: 8.4408. Min Act: -0.1700
Data Index: 3390568 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.1908. Min Range: -9.1908
Max Act: 8.4408. Min Act: -0.1700
Data Index: 4331372 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.1908. Min Range: -9.1908
Max Act: 8.4408. Min Act: -0.1700
Data Index: 5723688 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.1908. Min Range: -9.1908
Max Act: 8.4408. Min Act: -0.1700
Data Index: 6545091 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.1908. Min Range: -9.1908
Max Act: 8.5033. Min Act: -0.1700
Data Index: 1714032 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.1908. Min Range: -9.1908
Max Act: 8.3783. Min Act: -0.1700
Data Index: 4530179 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.1908. Min Range: -9.1908
Max Act: 8.3783. Min Act: -0.1700
Data Index: 6939682 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.1908. Min Range: -9.1908
Max Act: 8.3783. Min Act: -0.1700
Data Index: 4415591 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.1908. Min Range: -9.1908
Max Act: 8.3783. Min Act: -0.1700
Data Index: 4384725 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.1908. Min Range: -9.1908
Max Act: 8.3783. Min Act: -0.1700
Data Index: 492431 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.1908. Min Range: -9.1908
Max Act: 8.3783. Min Act: -0.1700
Data Index: 5902927 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #19