Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3572 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8489. Min Range: -5.8489
Max Act: 5.8489. Min Act: -0.1700
Data Index: 5377938 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8489. Min Range: -5.8489
Max Act: 5.8177. Min Act: -0.1700
Data Index: 5002062 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8489. Min Range: -5.8489
Max Act: 5.7552. Min Act: -0.1700
Data Index: 8373471 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8489. Min Range: -5.8489
Max Act: 5.6614. Min Act: -0.1700
Data Index: 740854 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8489. Min Range: -5.8489
Max Act: 5.6614. Min Act: -0.1700
Data Index: 1837007 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8489. Min Range: -5.8489
Max Act: 5.6302. Min Act: -0.1700
Data Index: 4860518 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8489. Min Range: -5.8489
Max Act: 5.5364. Min Act: -0.1700
Data Index: 4742744 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8489. Min Range: -5.8489
Max Act: 5.5052. Min Act: -0.1700
Data Index: 5065689 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8489. Min Range: -5.8489
Max Act: 5.5052. Min Act: -0.1700
Data Index: 1155762 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8489. Min Range: -5.8489
Max Act: 5.4739. Min Act: -0.1700
Data Index: 6331142 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8489. Min Range: -5.8489
Max Act: 5.4739. Min Act: -0.1700
Data Index: 312988 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8489. Min Range: -5.8489
Max Act: 5.4739. Min Act: -0.1700
Data Index: 172292 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8489. Min Range: -5.8489
Max Act: 5.4114. Min Act: -0.1700
Data Index: 24425 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8489. Min Range: -5.8489
Max Act: 5.3802. Min Act: -0.1700
Data Index: 7562047 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8489. Min Range: -5.8489
Max Act: 5.4114. Min Act: -0.1700
Data Index: 1592850 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8489. Min Range: -5.8489
Max Act: 5.4114. Min Act: -0.1700
Data Index: 1008211 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8489. Min Range: -5.8489
Max Act: 5.4114. Min Act: -0.1700
Data Index: 165577 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8489. Min Range: -5.8489
Max Act: 5.3802. Min Act: -0.1700
Data Index: 6996579 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8489. Min Range: -5.8489
Max Act: 5.3489. Min Act: -0.1700
Data Index: 6133962 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8489. Min Range: -5.8489
Max Act: 5.3489. Min Act: -0.1700
Data Index: 1542400 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #19