Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4703 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4805. Min Range: -6.4805
Max Act: 6.4805. Min Act: -0.1700
Data Index: 7048733 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4805. Min Range: -6.4805
Max Act: 6.3242. Min Act: -0.1700
Data Index: 6034712 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4805. Min Range: -6.4805
Max Act: 6.2930. Min Act: -0.1700
Data Index: 7291750 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4805. Min Range: -6.4805
Max Act: 6.2930. Min Act: -0.1700
Data Index: 8822958 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4805. Min Range: -6.4805
Max Act: 6.1992. Min Act: -0.1700
Data Index: 7314990 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4805. Min Range: -6.4805
Max Act: 6.1992. Min Act: -0.1700
Data Index: 2123131 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4805. Min Range: -6.4805
Max Act: 6.1992. Min Act: -0.1700
Data Index: 6980568 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4805. Min Range: -6.4805
Max Act: 6.1680. Min Act: -0.1700
Data Index: 7858891 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4805. Min Range: -6.4805
Max Act: 6.1992. Min Act: -0.1700
Data Index: 3901386 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4805. Min Range: -6.4805
Max Act: 6.1367. Min Act: -0.1700
Data Index: 7433866 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4805. Min Range: -6.4805
Max Act: 6.1992. Min Act: -0.1700
Data Index: 1418343 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4805. Min Range: -6.4805
Max Act: 6.1367. Min Act: -0.1700
Data Index: 392493 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4805. Min Range: -6.4805
Max Act: 6.1680. Min Act: -0.1700
Data Index: 2968895 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4805. Min Range: -6.4805
Max Act: 6.1367. Min Act: -0.1700
Data Index: 6601040 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4805. Min Range: -6.4805
Max Act: 6.1055. Min Act: -0.1700
Data Index: 3575720 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4805. Min Range: -6.4805
Max Act: 6.0430. Min Act: -0.1700
Data Index: 1271845 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4805. Min Range: -6.4805
Max Act: 6.0430. Min Act: -0.1700
Data Index: 7888004 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4805. Min Range: -6.4805
Max Act: 6.0430. Min Act: -0.1700
Data Index: 4234485 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4805. Min Range: -6.4805
Max Act: 6.0430. Min Act: -0.1700
Data Index: 842121 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4805. Min Range: -6.4805
Max Act: 6.0430. Min Act: -0.1700
Data Index: 7388590 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #19