Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 874 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8755. Min Range: -7.8755
Max Act: 7.8755. Min Act: -0.1700
Data Index: 2440694 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8755. Min Range: -7.8755
Max Act: 7.6255. Min Act: -0.1700
Data Index: 1341931 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8755. Min Range: -7.8755
Max Act: 7.4067. Min Act: -0.1700
Data Index: 7095982 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8755. Min Range: -7.8755
Max Act: 7.3442. Min Act: -0.1700
Data Index: 3188905 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8755. Min Range: -7.8755
Max Act: 7.2192. Min Act: -0.1700
Data Index: 5079228 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8755. Min Range: -7.8755
Max Act: 7.2192. Min Act: -0.1700
Data Index: 3290905 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8755. Min Range: -7.8755
Max Act: 7.2505. Min Act: -0.1700
Data Index: 4643864 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8755. Min Range: -7.8755
Max Act: 7.1880. Min Act: -0.1700
Data Index: 7669645 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8755. Min Range: -7.8755
Max Act: 7.1880. Min Act: -0.1700
Data Index: 2733093 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8755. Min Range: -7.8755
Max Act: 7.1567. Min Act: -0.1700
Data Index: 3990169 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8755. Min Range: -7.8755
Max Act: 7.1567. Min Act: -0.1700
Data Index: 6396888 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8755. Min Range: -7.8755
Max Act: 7.1567. Min Act: -0.1700
Data Index: 5633123 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8755. Min Range: -7.8755
Max Act: 7.1255. Min Act: -0.1700
Data Index: 7212477 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8755. Min Range: -7.8755
Max Act: 7.0942. Min Act: -0.1700
Data Index: 4929576 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8755. Min Range: -7.8755
Max Act: 7.0942. Min Act: -0.1700
Data Index: 1243249 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8755. Min Range: -7.8755
Max Act: 7.0942. Min Act: -0.1700
Data Index: 3530771 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8755. Min Range: -7.8755
Max Act: 7.0630. Min Act: -0.1700
Data Index: 4122849 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8755. Min Range: -7.8755
Max Act: 7.0942. Min Act: -0.1700
Data Index: 2471155 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8755. Min Range: -7.8755
Max Act: 7.0630. Min Act: -0.1700
Data Index: 438134 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8755. Min Range: -7.8755
Max Act: 7.0630. Min Act: -0.1700
Data Index: 7996190 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #19