Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2314 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.0596. Min Range: -4.0596
Max Act: 4.0596. Min Act: -0.1700
Data Index: 3158611 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0596. Min Range: -4.0596
Max Act: 4.0283. Min Act: -0.1700
Data Index: 1990228 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0596. Min Range: -4.0596
Max Act: 4.0283. Min Act: -0.1700
Data Index: 3198077 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0596. Min Range: -4.0596
Max Act: 3.9971. Min Act: -0.1700
Data Index: 1882722 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0596. Min Range: -4.0596
Max Act: 3.9971. Min Act: -0.1700
Data Index: 4697031 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0596. Min Range: -4.0596
Max Act: 3.9971. Min Act: -0.1700
Data Index: 6167689 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0596. Min Range: -4.0596
Max Act: 3.9971. Min Act: -0.1700
Data Index: 1044334 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0596. Min Range: -4.0596
Max Act: 3.9345. Min Act: -0.1700
Data Index: 4769852 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0596. Min Range: -4.0596
Max Act: 3.9345. Min Act: -0.1700
Data Index: 1807093 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0596. Min Range: -4.0596
Max Act: 3.9033. Min Act: -0.1700
Data Index: 5387987 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0596. Min Range: -4.0596
Max Act: 3.9345. Min Act: -0.1700
Data Index: 3371144 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0596. Min Range: -4.0596
Max Act: 3.9345. Min Act: -0.1700
Data Index: 5187174 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0596. Min Range: -4.0596
Max Act: 3.9033. Min Act: -0.1700
Data Index: 2167099 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0596. Min Range: -4.0596
Max Act: 3.9033. Min Act: -0.1700
Data Index: 8663615 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0596. Min Range: -4.0596
Max Act: 3.9345. Min Act: -0.1700
Data Index: 5355517 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0596. Min Range: -4.0596
Max Act: 3.9033. Min Act: -0.1700
Data Index: 458179 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0596. Min Range: -4.0596
Max Act: 3.8720. Min Act: -0.1700
Data Index: 979201 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0596. Min Range: -4.0596
Max Act: 3.8720. Min Act: -0.1700
Data Index: 4557131 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0596. Min Range: -4.0596
Max Act: 3.8407. Min Act: -0.1700
Data Index: 2270137 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0596. Min Range: -4.0596
Max Act: 3.8407. Min Act: -0.1700
Data Index: 1871382 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #19