Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1892 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3671. Min Range: -6.3671
Max Act: 6.3671. Min Act: -0.1700
Data Index: 5754105 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3671. Min Range: -6.3671
Max Act: 6.2108. Min Act: -0.1700
Data Index: 1094917 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3671. Min Range: -6.3671
Max Act: 6.2421. Min Act: -0.1700
Data Index: 635161 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3671. Min Range: -6.3671
Max Act: 6.2108. Min Act: -0.1700
Data Index: 1357855 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3671. Min Range: -6.3671
Max Act: 6.1796. Min Act: -0.1700
Data Index: 7412995 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3671. Min Range: -6.3671
Max Act: 6.1796. Min Act: -0.1700
Data Index: 2789151 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3671. Min Range: -6.3671
Max Act: 6.1171. Min Act: -0.1700
Data Index: 8629829 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3671. Min Range: -6.3671
Max Act: 6.0546. Min Act: -0.1700
Data Index: 72993 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3671. Min Range: -6.3671
Max Act: 6.0546. Min Act: -0.1700
Data Index: 8398993 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3671. Min Range: -6.3671
Max Act: 5.9921. Min Act: -0.1700
Data Index: 8402221 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3671. Min Range: -6.3671
Max Act: 5.9921. Min Act: -0.1700
Data Index: 7422934 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3671. Min Range: -6.3671
Max Act: 5.9921. Min Act: -0.1700
Data Index: 5424158 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3671. Min Range: -6.3671
Max Act: 5.9608. Min Act: -0.1700
Data Index: 7319787 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3671. Min Range: -6.3671
Max Act: 5.9608. Min Act: -0.1700
Data Index: 1003363 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3671. Min Range: -6.3671
Max Act: 5.9296. Min Act: -0.1700
Data Index: 6047747 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3671. Min Range: -6.3671
Max Act: 5.9296. Min Act: -0.1700
Data Index: 2745611 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3671. Min Range: -6.3671
Max Act: 5.9296. Min Act: -0.1700
Data Index: 1231430 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3671. Min Range: -6.3671
Max Act: 5.9296. Min Act: -0.1700
Data Index: 1913023 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3671. Min Range: -6.3671
Max Act: 5.8983. Min Act: -0.1700
Data Index: 4902054 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3671. Min Range: -6.3671
Max Act: 5.8671. Min Act: -0.1700
Data Index: 4989241 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #19