Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2675 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.3921. Min Range: -10.3921
Max Act: 10.3921. Min Act: -0.1700
Data Index: 7372591 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.3921. Min Range: -10.3921
Max Act: 9.9546. Min Act: -0.1700
Data Index: 3440818 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.3921. Min Range: -10.3921
Max Act: 9.8921. Min Act: -0.1700
Data Index: 4541561 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.3921. Min Range: -10.3921
Max Act: 9.8921. Min Act: -0.1700
Data Index: 2119169 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.3921. Min Range: -10.3921
Max Act: 9.8296. Min Act: -0.1700
Data Index: 4207393 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.3921. Min Range: -10.3921
Max Act: 9.7671. Min Act: -0.1698
Data Index: 4541562 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.3921. Min Range: -10.3921
Max Act: 9.7046. Min Act: -0.1700
Data Index: 8228510 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.3921. Min Range: -10.3921
Max Act: 9.7046. Min Act: -0.1700
Data Index: 736616 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.3921. Min Range: -10.3921
Max Act: 9.6421. Min Act: -0.1700
Data Index: 1795186 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.3921. Min Range: -10.3921
Max Act: 9.5796. Min Act: -0.1700
Data Index: 4180197 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.3921. Min Range: -10.3921
Max Act: 9.5796. Min Act: -0.1700
Data Index: 4503572 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.3921. Min Range: -10.3921
Max Act: 9.5796. Min Act: -0.1700
Data Index: 8077111 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.3921. Min Range: -10.3921
Max Act: 9.5171. Min Act: -0.1700
Data Index: 2119171 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.3921. Min Range: -10.3921
Max Act: 9.5171. Min Act: -0.1700
Data Index: 330202 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.3921. Min Range: -10.3921
Max Act: 9.4546. Min Act: -0.1700
Data Index: 8133202 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.3921. Min Range: -10.3921
Max Act: 9.5171. Min Act: -0.1700
Data Index: 6009785 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.3921. Min Range: -10.3921
Max Act: 9.5171. Min Act: -0.1700
Data Index: 1037690 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.3921. Min Range: -10.3921
Max Act: 9.5171. Min Act: -0.1700
Data Index: 7814562 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.3921. Min Range: -10.3921
Max Act: 9.5171. Min Act: -0.1699
Data Index: 3163032 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.3921. Min Range: -10.3921
Max Act: 9.5171. Min Act: -0.1700
Data Index: 1386371 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #19