Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2681 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.2124. Min Range: -9.2124
Max Act: 9.2124. Min Act: -0.1700
Data Index: 919219 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.2124. Min Range: -9.2124
Max Act: 9.2124. Min Act: -0.1700
Data Index: 1568205 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.2124. Min Range: -9.2124
Max Act: 9.1499. Min Act: -0.1700
Data Index: 5342010 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.2124. Min Range: -9.2124
Max Act: 9.0249. Min Act: -0.1700
Data Index: 191254 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.2124. Min Range: -9.2124
Max Act: 9.0249. Min Act: -0.1700
Data Index: 1653110 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.2124. Min Range: -9.2124
Max Act: 8.8374. Min Act: -0.1700
Data Index: 3787125 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.2124. Min Range: -9.2124
Max Act: 8.8999. Min Act: -0.1700
Data Index: 1930761 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.2124. Min Range: -9.2124
Max Act: 8.8999. Min Act: -0.1700
Data Index: 4335783 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.2124. Min Range: -9.2124
Max Act: 8.8374. Min Act: -0.1700
Data Index: 7520437 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.2124. Min Range: -9.2124
Max Act: 8.8374. Min Act: -0.1700
Data Index: 925089 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.2124. Min Range: -9.2124
Max Act: 8.7749. Min Act: -0.1700
Data Index: 2355404 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.2124. Min Range: -9.2124
Max Act: 8.7749. Min Act: -0.1700
Data Index: 7293666 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.2124. Min Range: -9.2124
Max Act: 8.7124. Min Act: -0.1700
Data Index: 3976102 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.2124. Min Range: -9.2124
Max Act: 8.7124. Min Act: -0.1700
Data Index: 3852956 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.2124. Min Range: -9.2124
Max Act: 8.7124. Min Act: -0.1700
Data Index: 6384459 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.2124. Min Range: -9.2124
Max Act: 8.7124. Min Act: -0.1700
Data Index: 7816258 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.2124. Min Range: -9.2124
Max Act: 8.6499. Min Act: -0.1700
Data Index: 6848068 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.2124. Min Range: -9.2124
Max Act: 8.6499. Min Act: -0.1700
Data Index: 204286 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.2124. Min Range: -9.2124
Max Act: 8.6499. Min Act: -0.1700
Data Index: 3315322 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.2124. Min Range: -9.2124
Max Act: 8.6499. Min Act: -0.1700
Data Index: 8204951 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #19