Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1108 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4160. Min Range: -7.4160
Max Act: 7.4160. Min Act: -0.1700
Data Index: 1876533 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4160. Min Range: -7.4160
Max Act: 7.1660. Min Act: -0.1700
Data Index: 7687505 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4160. Min Range: -7.4160
Max Act: 7.1972. Min Act: -0.1700
Data Index: 7454046 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4160. Min Range: -7.4160
Max Act: 7.1347. Min Act: -0.1700
Data Index: 1188665 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4160. Min Range: -7.4160
Max Act: 7.1035. Min Act: -0.1700
Data Index: 4355130 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4160. Min Range: -7.4160
Max Act: 7.1035. Min Act: -0.1700
Data Index: 8812240 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4160. Min Range: -7.4160
Max Act: 7.0097. Min Act: -0.1700
Data Index: 8052459 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4160. Min Range: -7.4160
Max Act: 7.0097. Min Act: -0.1700
Data Index: 7415534 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4160. Min Range: -7.4160
Max Act: 6.9785. Min Act: -0.1700
Data Index: 6383680 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4160. Min Range: -7.4160
Max Act: 6.9472. Min Act: -0.1700
Data Index: 1187654 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4160. Min Range: -7.4160
Max Act: 6.9472. Min Act: -0.1700
Data Index: 6054363 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4160. Min Range: -7.4160
Max Act: 6.9785. Min Act: -0.1700
Data Index: 3612702 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4160. Min Range: -7.4160
Max Act: 6.9160. Min Act: -0.1700
Data Index: 5328249 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4160. Min Range: -7.4160
Max Act: 6.8535. Min Act: -0.1700
Data Index: 1498532 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4160. Min Range: -7.4160
Max Act: 6.8535. Min Act: -0.1700
Data Index: 2498939 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4160. Min Range: -7.4160
Max Act: 6.7910. Min Act: -0.1700
Data Index: 3802925 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4160. Min Range: -7.4160
Max Act: 6.8535. Min Act: -0.1700
Data Index: 2542195 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4160. Min Range: -7.4160
Max Act: 6.7910. Min Act: -0.1700
Data Index: 2571837 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4160. Min Range: -7.4160
Max Act: 6.7910. Min Act: -0.1700
Data Index: 2811286 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4160. Min Range: -7.4160
Max Act: 6.7597. Min Act: -0.1700
Data Index: 3576336 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #19