Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3482 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8167. Min Range: -3.8167
Max Act: 3.8167. Min Act: -0.1700
Data Index: 1837473 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8167. Min Range: -3.8167
Max Act: 3.7541. Min Act: -0.1700
Data Index: 8436081 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8167. Min Range: -3.8167
Max Act: 3.6603. Min Act: -0.1700
Data Index: 4802681 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8167. Min Range: -3.8167
Max Act: 3.6603. Min Act: -0.1700
Data Index: 3162538 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8167. Min Range: -3.8167
Max Act: 3.6446. Min Act: -0.1700
Data Index: 5470437 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8167. Min Range: -3.8167
Max Act: 3.5820. Min Act: -0.1700
Data Index: 3239275 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8167. Min Range: -3.8167
Max Act: 3.5507. Min Act: -0.1700
Data Index: 4848620 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8167. Min Range: -3.8167
Max Act: 3.5507. Min Act: -0.1700
Data Index: 7417950 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8167. Min Range: -3.8167
Max Act: 3.5351. Min Act: -0.1700
Data Index: 376952 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8167. Min Range: -3.8167
Max Act: 3.5037. Min Act: -0.1700
Data Index: 6101654 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8167. Min Range: -3.8167
Max Act: 3.5037. Min Act: -0.1700
Data Index: 8097344 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8167. Min Range: -3.8167
Max Act: 3.4881. Min Act: -0.1700
Data Index: 3865921 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8167. Min Range: -3.8167
Max Act: 3.4724. Min Act: -0.1700
Data Index: 8022085 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8167. Min Range: -3.8167
Max Act: 3.4724. Min Act: -0.1700
Data Index: 3412745 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8167. Min Range: -3.8167
Max Act: 3.4567. Min Act: -0.1700
Data Index: 7881352 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8167. Min Range: -3.8167
Max Act: 3.4567. Min Act: -0.1700
Data Index: 8096084 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8167. Min Range: -3.8167
Max Act: 3.4567. Min Act: -0.1700
Data Index: 3523464 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8167. Min Range: -3.8167
Max Act: 3.4411. Min Act: -0.1700
Data Index: 1879101 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8167. Min Range: -3.8167
Max Act: 3.4567. Min Act: -0.1700
Data Index: 82593 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8167. Min Range: -3.8167
Max Act: 3.4567. Min Act: -0.1700
Data Index: 6349972 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #19