Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5293 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.1420. Min Range: -9.1420
Max Act: 9.1420. Min Act: -0.1700
Data Index: 7930662 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.1420. Min Range: -9.1420
Max Act: 9.1420. Min Act: -0.1700
Data Index: 2124960 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.1420. Min Range: -9.1420
Max Act: 9.0795. Min Act: -0.1700
Data Index: 3654294 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.1420. Min Range: -9.1420
Max Act: 9.0170. Min Act: -0.1700
Data Index: 7128362 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.1420. Min Range: -9.1420
Max Act: 8.8920. Min Act: -0.1700
Data Index: 7535672 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.1420. Min Range: -9.1420
Max Act: 8.8920. Min Act: -0.1700
Data Index: 2550386 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.1420. Min Range: -9.1420
Max Act: 8.8295. Min Act: -0.1700
Data Index: 8028357 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.1420. Min Range: -9.1420
Max Act: 8.8295. Min Act: -0.1700
Data Index: 5864584 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.1420. Min Range: -9.1420
Max Act: 8.8295. Min Act: -0.1700
Data Index: 78519 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.1420. Min Range: -9.1420
Max Act: 8.8295. Min Act: -0.1700
Data Index: 5489109 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.1420. Min Range: -9.1420
Max Act: 8.7670. Min Act: -0.1700
Data Index: 3619714 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.1420. Min Range: -9.1420
Max Act: 8.8295. Min Act: -0.1700
Data Index: 8516955 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.1420. Min Range: -9.1420
Max Act: 8.7670. Min Act: -0.1700
Data Index: 110763 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.1420. Min Range: -9.1420
Max Act: 8.7670. Min Act: -0.1700
Data Index: 5942056 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.1420. Min Range: -9.1420
Max Act: 8.7670. Min Act: -0.1700
Data Index: 4888418 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.1420. Min Range: -9.1420
Max Act: 8.7670. Min Act: -0.1700
Data Index: 6737129 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.1420. Min Range: -9.1420
Max Act: 8.7045. Min Act: -0.1700
Data Index: 2854599 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.1420. Min Range: -9.1420
Max Act: 8.7045. Min Act: -0.1700
Data Index: 1820390 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.1420. Min Range: -9.1420
Max Act: 8.7670. Min Act: -0.1700
Data Index: 2242283 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.1420. Min Range: -9.1420
Max Act: 8.7670. Min Act: -0.1700
Data Index: 409266 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #19