Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 568 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6796. Min Range: -6.6796
Max Act: 6.6796. Min Act: -0.1700
Data Index: 1245016 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6796. Min Range: -6.6796
Max Act: 6.5234. Min Act: -0.1700
Data Index: 871396 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6796. Min Range: -6.6796
Max Act: 6.4921. Min Act: -0.1700
Data Index: 2066415 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6796. Min Range: -6.6796
Max Act: 6.3359. Min Act: -0.1700
Data Index: 8135993 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6796. Min Range: -6.6796
Max Act: 6.3359. Min Act: -0.1700
Data Index: 6715588 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6796. Min Range: -6.6796
Max Act: 6.2421. Min Act: -0.1700
Data Index: 4060768 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6796. Min Range: -6.6796
Max Act: 6.2109. Min Act: -0.1700
Data Index: 5257960 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6796. Min Range: -6.6796
Max Act: 6.2109. Min Act: -0.1700
Data Index: 8247638 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6796. Min Range: -6.6796
Max Act: 6.1796. Min Act: -0.1700
Data Index: 471589 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6796. Min Range: -6.6796
Max Act: 6.1796. Min Act: -0.1700
Data Index: 5516704 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6796. Min Range: -6.6796
Max Act: 6.1796. Min Act: -0.1700
Data Index: 1008771 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6796. Min Range: -6.6796
Max Act: 6.1484. Min Act: -0.1700
Data Index: 108643 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6796. Min Range: -6.6796
Max Act: 6.1484. Min Act: -0.1700
Data Index: 1907161 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6796. Min Range: -6.6796
Max Act: 6.1484. Min Act: -0.1700
Data Index: 797731 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6796. Min Range: -6.6796
Max Act: 6.1484. Min Act: -0.1700
Data Index: 7471246 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6796. Min Range: -6.6796
Max Act: 6.1171. Min Act: -0.1700
Data Index: 4934723 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6796. Min Range: -6.6796
Max Act: 6.1171. Min Act: -0.1700
Data Index: 4819590 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6796. Min Range: -6.6796
Max Act: 6.1171. Min Act: -0.1700
Data Index: 8604456 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6796. Min Range: -6.6796
Max Act: 6.1171. Min Act: -0.1700
Data Index: 1697318 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6796. Min Range: -6.6796
Max Act: 6.0859. Min Act: -0.1700
Data Index: 363780 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #19