Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 27 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.9039. Min Range: -5.9039
Max Act: 5.9039. Min Act: -0.1700
Data Index: 4132501 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9039. Min Range: -5.9039
Max Act: 5.8726. Min Act: -0.1700
Data Index: 6006131 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9039. Min Range: -5.9039
Max Act: 5.8101. Min Act: -0.1700
Data Index: 4948567 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9039. Min Range: -5.9039
Max Act: 5.7789. Min Act: -0.1700
Data Index: 5090548 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9039. Min Range: -5.9039
Max Act: 5.7789. Min Act: -0.1700
Data Index: 8646915 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9039. Min Range: -5.9039
Max Act: 5.7476. Min Act: -0.1700
Data Index: 556439 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9039. Min Range: -5.9039
Max Act: 5.7164. Min Act: -0.1700
Data Index: 5389702 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9039. Min Range: -5.9039
Max Act: 5.7476. Min Act: -0.1700
Data Index: 6179618 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9039. Min Range: -5.9039
Max Act: 5.7164. Min Act: -0.1700
Data Index: 1194276 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9039. Min Range: -5.9039
Max Act: 5.7476. Min Act: -0.1700
Data Index: 9506 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9039. Min Range: -5.9039
Max Act: 5.7164. Min Act: -0.1700
Data Index: 7600301 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9039. Min Range: -5.9039
Max Act: 5.7164. Min Act: -0.1700
Data Index: 2586455 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9039. Min Range: -5.9039
Max Act: 5.6851. Min Act: -0.1700
Data Index: 1361470 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9039. Min Range: -5.9039
Max Act: 5.6851. Min Act: -0.1700
Data Index: 2293191 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9039. Min Range: -5.9039
Max Act: 5.6851. Min Act: -0.1700
Data Index: 2026146 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9039. Min Range: -5.9039
Max Act: 5.6851. Min Act: -0.1700
Data Index: 3243021 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9039. Min Range: -5.9039
Max Act: 5.6539. Min Act: -0.1700
Data Index: 1972126 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9039. Min Range: -5.9039
Max Act: 5.6539. Min Act: -0.1700
Data Index: 5307048 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9039. Min Range: -5.9039
Max Act: 5.6539. Min Act: -0.1700
Data Index: 2441343 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9039. Min Range: -5.9039
Max Act: 5.5914. Min Act: -0.1700
Data Index: 3419200 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #19