Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3195 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6124. Min Range: -5.6124
Max Act: 5.6124. Min Act: -0.1700
Data Index: 783315 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6124. Min Range: -5.6124
Max Act: 5.4874. Min Act: -0.1700
Data Index: 7108732 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6124. Min Range: -5.6124
Max Act: 5.4874. Min Act: -0.1700
Data Index: 5258691 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6124. Min Range: -5.6124
Max Act: 5.4874. Min Act: -0.1700
Data Index: 518486 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6124. Min Range: -5.6124
Max Act: 5.4562. Min Act: -0.1700
Data Index: 6457077 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6124. Min Range: -5.6124
Max Act: 5.4562. Min Act: -0.1700
Data Index: 1031799 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6124. Min Range: -5.6124
Max Act: 5.4562. Min Act: -0.1700
Data Index: 3081824 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6124. Min Range: -5.6124
Max Act: 5.3937. Min Act: -0.1700
Data Index: 3096544 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6124. Min Range: -5.6124
Max Act: 5.3937. Min Act: -0.1700
Data Index: 4841797 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6124. Min Range: -5.6124
Max Act: 5.2999. Min Act: -0.1700
Data Index: 1071935 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6124. Min Range: -5.6124
Max Act: 5.3312. Min Act: -0.1700
Data Index: 4709677 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6124. Min Range: -5.6124
Max Act: 5.2999. Min Act: -0.1700
Data Index: 916317 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6124. Min Range: -5.6124
Max Act: 5.2999. Min Act: -0.1700
Data Index: 8761489 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6124. Min Range: -5.6124
Max Act: 5.2999. Min Act: -0.1700
Data Index: 7186805 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6124. Min Range: -5.6124
Max Act: 5.2999. Min Act: -0.1700
Data Index: 4930567 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6124. Min Range: -5.6124
Max Act: 5.2687. Min Act: -0.1700
Data Index: 5375129 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6124. Min Range: -5.6124
Max Act: 5.2374. Min Act: -0.1700
Data Index: 6963527 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6124. Min Range: -5.6124
Max Act: 5.2687. Min Act: -0.1700
Data Index: 6544343 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6124. Min Range: -5.6124
Max Act: 5.2687. Min Act: -0.1700
Data Index: 3143633 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6124. Min Range: -5.6124
Max Act: 5.2374. Min Act: -0.1700
Data Index: 944975 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #19