Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2258 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4058. Min Range: -5.4058
Max Act: 5.3745. Min Act: -0.1700
Data Index: 7352705 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4058. Min Range: -5.4058
Max Act: 5.4058. Min Act: -0.1700
Data Index: 3450779 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4058. Min Range: -5.4058
Max Act: 5.3433. Min Act: -0.1700
Data Index: 2844601 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4058. Min Range: -5.4058
Max Act: 5.3433. Min Act: -0.1700
Data Index: 7480044 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4058. Min Range: -5.4058
Max Act: 5.3120. Min Act: -0.1700
Data Index: 3960875 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4058. Min Range: -5.4058
Max Act: 5.2495. Min Act: -0.1700
Data Index: 5463420 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4058. Min Range: -5.4058
Max Act: 5.2495. Min Act: -0.1700
Data Index: 2996735 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4058. Min Range: -5.4058
Max Act: 5.2183. Min Act: -0.1700
Data Index: 100384 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4058. Min Range: -5.4058
Max Act: 5.1870. Min Act: -0.1700
Data Index: 1733633 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4058. Min Range: -5.4058
Max Act: 5.1870. Min Act: -0.1700
Data Index: 781319 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4058. Min Range: -5.4058
Max Act: 5.1558. Min Act: -0.1700
Data Index: 1034146 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4058. Min Range: -5.4058
Max Act: 5.1870. Min Act: -0.1700
Data Index: 3330909 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4058. Min Range: -5.4058
Max Act: 5.1245. Min Act: -0.1700
Data Index: 3905179 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4058. Min Range: -5.4058
Max Act: 5.1245. Min Act: -0.1700
Data Index: 6629586 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4058. Min Range: -5.4058
Max Act: 5.0933. Min Act: -0.1700
Data Index: 7501940 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4058. Min Range: -5.4058
Max Act: 5.0620. Min Act: -0.1700
Data Index: 7789115 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4058. Min Range: -5.4058
Max Act: 5.0620. Min Act: -0.1700
Data Index: 758469 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4058. Min Range: -5.4058
Max Act: 5.0933. Min Act: -0.1700
Data Index: 1416315 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4058. Min Range: -5.4058
Max Act: 5.0933. Min Act: -0.1700
Data Index: 2476703 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4058. Min Range: -5.4058
Max Act: 5.0933. Min Act: -0.1700
Data Index: 5191864 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #19