Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3360 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9004. Min Range: -4.9004
Max Act: 4.9004. Min Act: -0.1700
Data Index: 1458089 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9004. Min Range: -4.9004
Max Act: 4.9004. Min Act: -0.1700
Data Index: 928087 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9004. Min Range: -4.9004
Max Act: 4.8067. Min Act: -0.1700
Data Index: 8155256 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9004. Min Range: -4.9004
Max Act: 4.7754. Min Act: -0.1700
Data Index: 5555816 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9004. Min Range: -4.9004
Max Act: 4.6817. Min Act: -0.1700
Data Index: 3079099 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9004. Min Range: -4.9004
Max Act: 4.6504. Min Act: -0.1700
Data Index: 2925338 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9004. Min Range: -4.9004
Max Act: 4.6504. Min Act: -0.1700
Data Index: 4077892 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9004. Min Range: -4.9004
Max Act: 4.6504. Min Act: -0.1700
Data Index: 2648302 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9004. Min Range: -4.9004
Max Act: 4.6504. Min Act: -0.1700
Data Index: 8622517 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9004. Min Range: -4.9004
Max Act: 4.6504. Min Act: -0.1700
Data Index: 3935115 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9004. Min Range: -4.9004
Max Act: 4.6192. Min Act: -0.1700
Data Index: 4045030 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9004. Min Range: -4.9004
Max Act: 4.5879. Min Act: -0.1700
Data Index: 5333691 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9004. Min Range: -4.9004
Max Act: 4.6192. Min Act: -0.1700
Data Index: 6923013 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9004. Min Range: -4.9004
Max Act: 4.5879. Min Act: -0.1700
Data Index: 5657072 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9004. Min Range: -4.9004
Max Act: 4.5567. Min Act: -0.1700
Data Index: 5266341 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9004. Min Range: -4.9004
Max Act: 4.5567. Min Act: -0.1700
Data Index: 1471958 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9004. Min Range: -4.9004
Max Act: 4.5567. Min Act: -0.1700
Data Index: 8691171 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9004. Min Range: -4.9004
Max Act: 4.5567. Min Act: -0.1700
Data Index: 3424557 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9004. Min Range: -4.9004
Max Act: 4.5567. Min Act: -0.1700
Data Index: 3948281 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9004. Min Range: -4.9004
Max Act: 4.5567. Min Act: -0.1700
Data Index: 8805727 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #19