Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 5093 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.3268. Min Range: -6.3268
Max Act: 6.3268. Min Act: -0.1700
Data Index: 5677535 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3268. Min Range: -6.3268
Max Act: 6.2018. Min Act: -0.1700
Data Index: 8621108 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3268. Min Range: -6.3268
Max Act: 6.2018. Min Act: -0.1700
Data Index: 8824771 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3268. Min Range: -6.3268
Max Act: 6.1393. Min Act: -0.1700
Data Index: 1752995 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3268. Min Range: -6.3268
Max Act: 6.0768. Min Act: -0.1700
Data Index: 1061980 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3268. Min Range: -6.3268
Max Act: 6.0768. Min Act: -0.1700
Data Index: 8464403 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3268. Min Range: -6.3268
Max Act: 6.0768. Min Act: -0.1700
Data Index: 1102171 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3268. Min Range: -6.3268
Max Act: 6.0143. Min Act: -0.1700
Data Index: 700024 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3268. Min Range: -6.3268
Max Act: 6.0143. Min Act: -0.1700
Data Index: 4512347 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3268. Min Range: -6.3268
Max Act: 5.9830. Min Act: -0.1700
Data Index: 3211922 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3268. Min Range: -6.3268
Max Act: 5.9205. Min Act: -0.1700
Data Index: 893462 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3268. Min Range: -6.3268
Max Act: 5.9518. Min Act: -0.1700
Data Index: 4714514 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3268. Min Range: -6.3268
Max Act: 5.9518. Min Act: -0.1700
Data Index: 8145206 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3268. Min Range: -6.3268
Max Act: 5.9205. Min Act: -0.1700
Data Index: 8682903 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3268. Min Range: -6.3268
Max Act: 5.9518. Min Act: -0.1700
Data Index: 5090998 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3268. Min Range: -6.3268
Max Act: 5.8893. Min Act: -0.1700
Data Index: 7840554 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3268. Min Range: -6.3268
Max Act: 5.8580. Min Act: -0.1700
Data Index: 176680 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3268. Min Range: -6.3268
Max Act: 5.8268. Min Act: -0.1700
Data Index: 7570452 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3268. Min Range: -6.3268
Max Act: 5.8580. Min Act: -0.1700
Data Index: 6302480 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3268. Min Range: -6.3268
Max Act: 5.8580. Min Act: -0.1700
Data Index: 720681 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #19