Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3827 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.2192. Min Range: -9.2192
Max Act: 9.2192. Min Act: -0.1700
Data Index: 1789938 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.2192. Min Range: -9.2192
Max Act: 9.0942. Min Act: -0.1700
Data Index: 4946199 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.2192. Min Range: -9.2192
Max Act: 8.8442. Min Act: -0.1700
Data Index: 6604341 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.2192. Min Range: -9.2192
Max Act: 8.6567. Min Act: -0.1700
Data Index: 7386829 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.2192. Min Range: -9.2192
Max Act: 8.6567. Min Act: -0.1700
Data Index: 6725201 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.2192. Min Range: -9.2192
Max Act: 8.6567. Min Act: -0.1700
Data Index: 1885573 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.2192. Min Range: -9.2192
Max Act: 8.5317. Min Act: -0.1700
Data Index: 1625495 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.2192. Min Range: -9.2192
Max Act: 8.5317. Min Act: -0.1700
Data Index: 1983178 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.2192. Min Range: -9.2192
Max Act: 8.5317. Min Act: -0.1700
Data Index: 1183733 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.2192. Min Range: -9.2192
Max Act: 8.5317. Min Act: -0.1700
Data Index: 5035938 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.2192. Min Range: -9.2192
Max Act: 8.5317. Min Act: -0.1700
Data Index: 6165968 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.2192. Min Range: -9.2192
Max Act: 8.4692. Min Act: -0.1700
Data Index: 6549424 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.2192. Min Range: -9.2192
Max Act: 8.4692. Min Act: -0.1700
Data Index: 1620659 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.2192. Min Range: -9.2192
Max Act: 8.4067. Min Act: -0.1700
Data Index: 7286220 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.2192. Min Range: -9.2192
Max Act: 8.4067. Min Act: -0.1700
Data Index: 6716705 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.2192. Min Range: -9.2192
Max Act: 8.4067. Min Act: -0.1700
Data Index: 6768076 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.2192. Min Range: -9.2192
Max Act: 8.4067. Min Act: -0.1700
Data Index: 3941465 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.2192. Min Range: -9.2192
Max Act: 8.4067. Min Act: -0.1700
Data Index: 1158070 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.2192. Min Range: -9.2192
Max Act: 8.4067. Min Act: -0.1700
Data Index: 1975028 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.2192. Min Range: -9.2192
Max Act: 8.4067. Min Act: -0.1700
Data Index: 6554713 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #19