Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2740 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9219. Min Range: -3.9219
Max Act: 3.8906. Min Act: -0.1700
Data Index: 7766629 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9219. Min Range: -3.9219
Max Act: 3.8906. Min Act: -0.1700
Data Index: 8045995 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9219. Min Range: -3.9219
Max Act: 3.8906. Min Act: -0.1700
Data Index: 5095569 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9219. Min Range: -3.9219
Max Act: 3.8906. Min Act: -0.1700
Data Index: 5635417 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9219. Min Range: -3.9219
Max Act: 3.9219. Min Act: -0.1700
Data Index: 6044053 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9219. Min Range: -3.9219
Max Act: 3.8593. Min Act: -0.1700
Data Index: 3440664 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9219. Min Range: -3.9219
Max Act: 3.8280. Min Act: -0.1700
Data Index: 8563400 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9219. Min Range: -3.9219
Max Act: 3.8280. Min Act: -0.1700
Data Index: 849744 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9219. Min Range: -3.9219
Max Act: 3.7968. Min Act: -0.1700
Data Index: 693264 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9219. Min Range: -3.9219
Max Act: 3.7968. Min Act: -0.1700
Data Index: 4994507 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9219. Min Range: -3.9219
Max Act: 3.7968. Min Act: -0.1700
Data Index: 122332 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9219. Min Range: -3.9219
Max Act: 3.7655. Min Act: -0.1700
Data Index: 6324689 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9219. Min Range: -3.9219
Max Act: 3.7655. Min Act: -0.1700
Data Index: 1460512 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9219. Min Range: -3.9219
Max Act: 3.7655. Min Act: -0.1700
Data Index: 381512 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9219. Min Range: -3.9219
Max Act: 3.7342. Min Act: -0.1700
Data Index: 8318489 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9219. Min Range: -3.9219
Max Act: 3.7342. Min Act: -0.1700
Data Index: 8012923 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9219. Min Range: -3.9219
Max Act: 3.7342. Min Act: -0.1700
Data Index: 6108310 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9219. Min Range: -3.9219
Max Act: 3.7186. Min Act: -0.1700
Data Index: 3699772 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9219. Min Range: -3.9219
Max Act: 3.7186. Min Act: -0.1700
Data Index: 5029170 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9219. Min Range: -3.9219
Max Act: 3.7186. Min Act: -0.1700
Data Index: 3627815 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #19