Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3430 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.1972. Min Range: -4.1972
Max Act: 4.1972. Min Act: -0.1700
Data Index: 8805717 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1972. Min Range: -4.1972
Max Act: 4.0722. Min Act: -0.1700
Data Index: 4969967 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1972. Min Range: -4.1972
Max Act: 4.0722. Min Act: -0.1700
Data Index: 3403542 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1972. Min Range: -4.1972
Max Act: 3.9784. Min Act: -0.1700
Data Index: 6447280 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1972. Min Range: -4.1972
Max Act: 3.9784. Min Act: -0.1700
Data Index: 5826267 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1972. Min Range: -4.1972
Max Act: 3.9784. Min Act: -0.1700
Data Index: 5554849 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1972. Min Range: -4.1972
Max Act: 3.9471. Min Act: -0.1700
Data Index: 3575944 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1972. Min Range: -4.1972
Max Act: 3.9159. Min Act: -0.1700
Data Index: 4880765 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1972. Min Range: -4.1972
Max Act: 3.9159. Min Act: -0.1700
Data Index: 4265299 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1972. Min Range: -4.1972
Max Act: 3.8533. Min Act: -0.1700
Data Index: 1643268 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1972. Min Range: -4.1972
Max Act: 3.8533. Min Act: -0.1700
Data Index: 8733086 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1972. Min Range: -4.1972
Max Act: 3.8846. Min Act: -0.1700
Data Index: 7493840 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1972. Min Range: -4.1972
Max Act: 3.8533. Min Act: -0.1700
Data Index: 7105037 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1972. Min Range: -4.1972
Max Act: 3.8533. Min Act: -0.1700
Data Index: 5576931 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1972. Min Range: -4.1972
Max Act: 3.8533. Min Act: -0.1700
Data Index: 3937820 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1972. Min Range: -4.1972
Max Act: 3.8221. Min Act: -0.1700
Data Index: 635151 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1972. Min Range: -4.1972
Max Act: 3.7908. Min Act: -0.1700
Data Index: 1404111 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1972. Min Range: -4.1972
Max Act: 3.8221. Min Act: -0.1700
Data Index: 6447281 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1972. Min Range: -4.1972
Max Act: 3.8221. Min Act: -0.1700
Data Index: 5329590 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1972. Min Range: -4.1972
Max Act: 3.8221. Min Act: -0.1700
Data Index: 6029386 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #19