Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1598 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 11.1213. Min Range: -11.1213
Max Act: 11.1213. Min Act: -0.1700
Data Index: 2611366 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.1213. Min Range: -11.1213
Max Act: 11.0588. Min Act: -0.1700
Data Index: 5777287 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.1213. Min Range: -11.1213
Max Act: 11.0588. Min Act: -0.1700
Data Index: 866398 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.1213. Min Range: -11.1213
Max Act: 10.9338. Min Act: -0.1700
Data Index: 5021217 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.1213. Min Range: -11.1213
Max Act: 10.9338. Min Act: -0.1700
Data Index: 1226088 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.1213. Min Range: -11.1213
Max Act: 10.8088. Min Act: -0.1700
Data Index: 431982 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.1213. Min Range: -11.1213
Max Act: 10.6213. Min Act: -0.1700
Data Index: 8795911 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.1213. Min Range: -11.1213
Max Act: 10.4963. Min Act: -0.1700
Data Index: 29896 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.1213. Min Range: -11.1213
Max Act: 10.3088. Min Act: -0.1700
Data Index: 3915974 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.1213. Min Range: -11.1213
Max Act: 10.3088. Min Act: -0.1700
Data Index: 335814 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.1213. Min Range: -11.1213
Max Act: 10.3088. Min Act: -0.1700
Data Index: 3634003 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.1213. Min Range: -11.1213
Max Act: 10.3088. Min Act: -0.1699
Data Index: 7719109 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.1213. Min Range: -11.1213
Max Act: 10.3088. Min Act: -0.1700
Data Index: 3136918 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.1213. Min Range: -11.1213
Max Act: 10.3088. Min Act: -0.1700
Data Index: 6501708 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.1213. Min Range: -11.1213
Max Act: 10.3088. Min Act: -0.1700
Data Index: 3412028 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.1213. Min Range: -11.1213
Max Act: 10.2463. Min Act: -0.1700
Data Index: 5851968 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.1213. Min Range: -11.1213
Max Act: 10.2463. Min Act: -0.1700
Data Index: 2929481 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.1213. Min Range: -11.1213
Max Act: 10.2463. Min Act: -0.1700
Data Index: 7743062 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.1213. Min Range: -11.1213
Max Act: 10.1213. Min Act: -0.1700
Data Index: 2395538 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.1213. Min Range: -11.1213
Max Act: 10.1213. Min Act: -0.1700
Data Index: 551852 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #19