Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4946 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3546. Min Range: -5.3546
Max Act: 5.3546. Min Act: -0.1700
Data Index: 5755763 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3546. Min Range: -5.3546
Max Act: 5.0108. Min Act: -0.1700
Data Index: 3559465 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3546. Min Range: -5.3546
Max Act: 4.8233. Min Act: -0.1700
Data Index: 5865059 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3546. Min Range: -5.3546
Max Act: 4.8233. Min Act: -0.1700
Data Index: 5954522 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3546. Min Range: -5.3546
Max Act: 4.7921. Min Act: -0.1700
Data Index: 7110040 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3546. Min Range: -5.3546
Max Act: 4.7921. Min Act: -0.1700
Data Index: 2105862 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3546. Min Range: -5.3546
Max Act: 4.7921. Min Act: -0.1700
Data Index: 8484565 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3546. Min Range: -5.3546
Max Act: 4.7921. Min Act: -0.1700
Data Index: 6818357 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3546. Min Range: -5.3546
Max Act: 4.7296. Min Act: -0.1700
Data Index: 701480 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3546. Min Range: -5.3546
Max Act: 4.7296. Min Act: -0.1700
Data Index: 7129170 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3546. Min Range: -5.3546
Max Act: 4.7296. Min Act: -0.1700
Data Index: 7625698 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3546. Min Range: -5.3546
Max Act: 4.7296. Min Act: -0.1700
Data Index: 4507888 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3546. Min Range: -5.3546
Max Act: 4.6983. Min Act: -0.1700
Data Index: 5627235 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3546. Min Range: -5.3546
Max Act: 4.6358. Min Act: -0.1700
Data Index: 5999777 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3546. Min Range: -5.3546
Max Act: 4.6671. Min Act: -0.1700
Data Index: 2468479 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3546. Min Range: -5.3546
Max Act: 4.6671. Min Act: -0.1700
Data Index: 4230622 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3546. Min Range: -5.3546
Max Act: 4.6671. Min Act: -0.1700
Data Index: 7876499 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3546. Min Range: -5.3546
Max Act: 4.6358. Min Act: -0.1700
Data Index: 2949969 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3546. Min Range: -5.3546
Max Act: 4.6671. Min Act: -0.1700
Data Index: 6398076 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3546. Min Range: -5.3546
Max Act: 4.6671. Min Act: -0.1700
Data Index: 2131496 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #19