Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1042 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.7929. Min Range: -8.7929
Max Act: 8.7929. Min Act: -0.1700
Data Index: 4062849 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7929. Min Range: -8.7929
Max Act: 8.6054. Min Act: -0.1700
Data Index: 7651465 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7929. Min Range: -8.7929
Max Act: 8.6679. Min Act: -0.1700
Data Index: 8520250 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7929. Min Range: -8.7929
Max Act: 8.5429. Min Act: -0.1700
Data Index: 1868043 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7929. Min Range: -8.7929
Max Act: 8.4179. Min Act: -0.1700
Data Index: 1103852 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7929. Min Range: -8.7929
Max Act: 8.2304. Min Act: -0.1700
Data Index: 155082 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7929. Min Range: -8.7929
Max Act: 8.1679. Min Act: -0.1700
Data Index: 7739284 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7929. Min Range: -8.7929
Max Act: 8.1679. Min Act: -0.1700
Data Index: 3661553 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7929. Min Range: -8.7929
Max Act: 8.1679. Min Act: -0.1700
Data Index: 769189 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7929. Min Range: -8.7929
Max Act: 8.1054. Min Act: -0.1700
Data Index: 860582 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7929. Min Range: -8.7929
Max Act: 8.1054. Min Act: -0.1700
Data Index: 406587 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7929. Min Range: -8.7929
Max Act: 8.0429. Min Act: -0.1700
Data Index: 8345559 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7929. Min Range: -8.7929
Max Act: 8.0429. Min Act: -0.1700
Data Index: 6931009 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7929. Min Range: -8.7929
Max Act: 8.0429. Min Act: -0.1700
Data Index: 6441821 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7929. Min Range: -8.7929
Max Act: 7.9804. Min Act: -0.1700
Data Index: 5242185 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7929. Min Range: -8.7929
Max Act: 8.0429. Min Act: -0.1700
Data Index: 1076979 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7929. Min Range: -8.7929
Max Act: 7.9804. Min Act: -0.1700
Data Index: 4089642 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7929. Min Range: -8.7929
Max Act: 7.9804. Min Act: -0.1700
Data Index: 5502806 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7929. Min Range: -8.7929
Max Act: 7.9179. Min Act: -0.1700
Data Index: 7706993 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7929. Min Range: -8.7929
Max Act: 7.9804. Min Act: -0.1700
Data Index: 2964804 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #19