Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3484 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4671. Min Range: -7.4671
Max Act: 7.4671. Min Act: -0.1700
Data Index: 6067314 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4671. Min Range: -7.4671
Max Act: 7.2171. Min Act: -0.1700
Data Index: 4519874 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4671. Min Range: -7.4671
Max Act: 7.2171. Min Act: -0.1700
Data Index: 2666318 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4671. Min Range: -7.4671
Max Act: 7.2171. Min Act: -0.1700
Data Index: 8379111 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4671. Min Range: -7.4671
Max Act: 7.1234. Min Act: -0.1700
Data Index: 5094073 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4671. Min Range: -7.4671
Max Act: 7.0921. Min Act: -0.1700
Data Index: 5745604 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4671. Min Range: -7.4671
Max Act: 7.0609. Min Act: -0.1700
Data Index: 8587943 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4671. Min Range: -7.4671
Max Act: 6.9984. Min Act: -0.1700
Data Index: 4519450 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4671. Min Range: -7.4671
Max Act: 6.9984. Min Act: -0.1700
Data Index: 1790757 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4671. Min Range: -7.4671
Max Act: 7.0296. Min Act: -0.1700
Data Index: 4691920 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4671. Min Range: -7.4671
Max Act: 6.9359. Min Act: -0.1700
Data Index: 4462616 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4671. Min Range: -7.4671
Max Act: 6.9359. Min Act: -0.1700
Data Index: 4062319 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4671. Min Range: -7.4671
Max Act: 6.9046. Min Act: -0.1700
Data Index: 381720 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4671. Min Range: -7.4671
Max Act: 6.9046. Min Act: -0.1700
Data Index: 6795800 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4671. Min Range: -7.4671
Max Act: 6.8421. Min Act: -0.1700
Data Index: 7166089 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4671. Min Range: -7.4671
Max Act: 6.8421. Min Act: -0.1700
Data Index: 204287 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4671. Min Range: -7.4671
Max Act: 6.8109. Min Act: -0.1700
Data Index: 2672212 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4671. Min Range: -7.4671
Max Act: 6.8109. Min Act: -0.1700
Data Index: 1628877 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4671. Min Range: -7.4671
Max Act: 6.8109. Min Act: -0.1700
Data Index: 6370799 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4671. Min Range: -7.4671
Max Act: 6.8109. Min Act: -0.1700
Data Index: 223319 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #19