Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2929 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.0895. Min Range: -3.0895
Max Act: 3.0895. Min Act: -0.1700
Data Index: 182749 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0895. Min Range: -3.0895
Max Act: 3.0895. Min Act: -0.1700
Data Index: 6811359 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0895. Min Range: -3.0895
Max Act: 3.0737. Min Act: -0.1700
Data Index: 2551104 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0895. Min Range: -3.0895
Max Act: 3.0580. Min Act: -0.1700
Data Index: 2253521 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0895. Min Range: -3.0895
Max Act: 3.0422. Min Act: -0.1700
Data Index: 818713 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0895. Min Range: -3.0895
Max Act: 3.0264. Min Act: -0.1700
Data Index: 6561799 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0895. Min Range: -3.0895
Max Act: 3.0264. Min Act: -0.1700
Data Index: 4500266 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0895. Min Range: -3.0895
Max Act: 3.0264. Min Act: -0.1700
Data Index: 4877277 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0895. Min Range: -3.0895
Max Act: 2.9948. Min Act: -0.1700
Data Index: 603170 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0895. Min Range: -3.0895
Max Act: 2.9790. Min Act: -0.1700
Data Index: 305356 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0895. Min Range: -3.0895
Max Act: 2.9790. Min Act: -0.1700
Data Index: 89749 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0895. Min Range: -3.0895
Max Act: 2.9790. Min Act: -0.1700
Data Index: 512240 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0895. Min Range: -3.0895
Max Act: 2.9790. Min Act: -0.1700
Data Index: 4680164 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0895. Min Range: -3.0895
Max Act: 2.9632. Min Act: -0.1700
Data Index: 3603094 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0895. Min Range: -3.0895
Max Act: 2.9632. Min Act: -0.1700
Data Index: 5268040 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0895. Min Range: -3.0895
Max Act: 2.9473. Min Act: -0.1700
Data Index: 8641712 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0895. Min Range: -3.0895
Max Act: 2.9790. Min Act: -0.1700
Data Index: 8582091 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0895. Min Range: -3.0895
Max Act: 2.9632. Min Act: -0.1700
Data Index: 1164271 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0895. Min Range: -3.0895
Max Act: 2.9632. Min Act: -0.1700
Data Index: 2652982 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0895. Min Range: -3.0895
Max Act: 2.9473. Min Act: -0.1700
Data Index: 3211083 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #19