Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3495 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.1413. Min Range: -5.1413
Max Act: 5.1101. Min Act: -0.1700
Data Index: 3511158 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1413. Min Range: -5.1413
Max Act: 5.1413. Min Act: -0.1700
Data Index: 1605360 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1413. Min Range: -5.1413
Max Act: 5.1101. Min Act: -0.1700
Data Index: 1243266 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1413. Min Range: -5.1413
Max Act: 5.0476. Min Act: -0.1700
Data Index: 4575155 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1413. Min Range: -5.1413
Max Act: 5.0476. Min Act: -0.1700
Data Index: 6920822 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1413. Min Range: -5.1413
Max Act: 5.0163. Min Act: -0.1700
Data Index: 3276794 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1413. Min Range: -5.1413
Max Act: 5.0163. Min Act: -0.1700
Data Index: 5512636 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1413. Min Range: -5.1413
Max Act: 4.9851. Min Act: -0.1700
Data Index: 7917094 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1413. Min Range: -5.1413
Max Act: 4.9851. Min Act: -0.1700
Data Index: 5068217 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1413. Min Range: -5.1413
Max Act: 4.9538. Min Act: -0.1700
Data Index: 947870 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1413. Min Range: -5.1413
Max Act: 4.9226. Min Act: -0.1700
Data Index: 6826484 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1413. Min Range: -5.1413
Max Act: 4.9226. Min Act: -0.1700
Data Index: 6954990 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1413. Min Range: -5.1413
Max Act: 4.8913. Min Act: -0.1700
Data Index: 2036995 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1413. Min Range: -5.1413
Max Act: 4.9226. Min Act: -0.1700
Data Index: 2363647 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1413. Min Range: -5.1413
Max Act: 4.9226. Min Act: -0.1700
Data Index: 2693990 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1413. Min Range: -5.1413
Max Act: 4.9226. Min Act: -0.1700
Data Index: 2325430 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1413. Min Range: -5.1413
Max Act: 4.8913. Min Act: -0.1700
Data Index: 5619503 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1413. Min Range: -5.1413
Max Act: 4.8913. Min Act: -0.1700
Data Index: 6782613 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1413. Min Range: -5.1413
Max Act: 4.8913. Min Act: -0.1700
Data Index: 1108540 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1413. Min Range: -5.1413
Max Act: 4.8913. Min Act: -0.1700
Data Index: 3653197 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #19