Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4970 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7051. Min Range: -5.7051
Max Act: 5.6739. Min Act: -0.1700
Data Index: 6007017 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7051. Min Range: -5.7051
Max Act: 5.6426. Min Act: -0.1700
Data Index: 2948902 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7051. Min Range: -5.7051
Max Act: 5.6739. Min Act: -0.1700
Data Index: 3183303 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7051. Min Range: -5.7051
Max Act: 5.6739. Min Act: -0.1700
Data Index: 7079546 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7051. Min Range: -5.7051
Max Act: 5.7051. Min Act: -0.1700
Data Index: 2885092 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7051. Min Range: -5.7051
Max Act: 5.6739. Min Act: -0.1700
Data Index: 8161688 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7051. Min Range: -5.7051
Max Act: 5.6426. Min Act: -0.1700
Data Index: 5006362 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7051. Min Range: -5.7051
Max Act: 5.6426. Min Act: -0.1700
Data Index: 4640798 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7051. Min Range: -5.7051
Max Act: 5.6426. Min Act: -0.1700
Data Index: 2885089 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7051. Min Range: -5.7051
Max Act: 5.6114. Min Act: -0.1700
Data Index: 2878000 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7051. Min Range: -5.7051
Max Act: 5.6114. Min Act: -0.1700
Data Index: 5163486 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7051. Min Range: -5.7051
Max Act: 5.6114. Min Act: -0.1700
Data Index: 2878015 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7051. Min Range: -5.7051
Max Act: 5.5801. Min Act: -0.1700
Data Index: 5530338 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7051. Min Range: -5.7051
Max Act: 5.5801. Min Act: -0.1700
Data Index: 3347370 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7051. Min Range: -5.7051
Max Act: 5.5176. Min Act: -0.1700
Data Index: 1077439 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7051. Min Range: -5.7051
Max Act: 5.5489. Min Act: -0.1700
Data Index: 2885091 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7051. Min Range: -5.7051
Max Act: 5.5489. Min Act: -0.1700
Data Index: 1634174 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7051. Min Range: -5.7051
Max Act: 5.5489. Min Act: -0.1700
Data Index: 1720452 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7051. Min Range: -5.7051
Max Act: 5.5489. Min Act: -0.1700
Data Index: 6734188 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7051. Min Range: -5.7051
Max Act: 5.5489. Min Act: -0.1700
Data Index: 1971532 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #19