Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1327 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.1755. Min Range: -6.1755
Max Act: 6.1755. Min Act: -0.1700
Data Index: 3876109 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1755. Min Range: -6.1755
Max Act: 6.0505. Min Act: -0.1700
Data Index: 5554098 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1755. Min Range: -6.1755
Max Act: 6.0505. Min Act: -0.1700
Data Index: 4649289 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1755. Min Range: -6.1755
Max Act: 6.0505. Min Act: -0.1700
Data Index: 8404956 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1755. Min Range: -6.1755
Max Act: 5.9880. Min Act: -0.1700
Data Index: 8762759 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1755. Min Range: -6.1755
Max Act: 5.9255. Min Act: -0.1700
Data Index: 7381161 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1755. Min Range: -6.1755
Max Act: 5.8943. Min Act: -0.1700
Data Index: 3920559 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1755. Min Range: -6.1755
Max Act: 5.9255. Min Act: -0.1700
Data Index: 6914903 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1755. Min Range: -6.1755
Max Act: 5.8943. Min Act: -0.1700
Data Index: 4112536 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1755. Min Range: -6.1755
Max Act: 5.8943. Min Act: -0.1700
Data Index: 7278787 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1755. Min Range: -6.1755
Max Act: 5.8318. Min Act: -0.1700
Data Index: 3113437 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1755. Min Range: -6.1755
Max Act: 5.8318. Min Act: -0.1700
Data Index: 6411746 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1755. Min Range: -6.1755
Max Act: 5.8318. Min Act: -0.1700
Data Index: 4460235 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1755. Min Range: -6.1755
Max Act: 5.8318. Min Act: -0.1700
Data Index: 8046404 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1755. Min Range: -6.1755
Max Act: 5.8630. Min Act: -0.1700
Data Index: 4560369 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1755. Min Range: -6.1755
Max Act: 5.8005. Min Act: -0.1700
Data Index: 608253 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1755. Min Range: -6.1755
Max Act: 5.7693. Min Act: -0.1700
Data Index: 3857827 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1755. Min Range: -6.1755
Max Act: 5.8318. Min Act: -0.1700
Data Index: 38708 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1755. Min Range: -6.1755
Max Act: 5.8005. Min Act: -0.1700
Data Index: 4560357 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1755. Min Range: -6.1755
Max Act: 5.7068. Min Act: -0.1700
Data Index: 4012519 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #19