Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3509 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7490. Min Range: -5.7490
Max Act: 5.6865. Min Act: -0.1700
Data Index: 4903649 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7490. Min Range: -5.7490
Max Act: 5.7490. Min Act: -0.1700
Data Index: 4441245 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7490. Min Range: -5.7490
Max Act: 5.7178. Min Act: -0.1700
Data Index: 4162472 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7490. Min Range: -5.7490
Max Act: 5.6865. Min Act: -0.1700
Data Index: 3751634 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7490. Min Range: -5.7490
Max Act: 5.6865. Min Act: -0.1700
Data Index: 8177097 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7490. Min Range: -5.7490
Max Act: 5.6553. Min Act: -0.1700
Data Index: 4201776 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7490. Min Range: -5.7490
Max Act: 5.6553. Min Act: -0.1700
Data Index: 7170960 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7490. Min Range: -5.7490
Max Act: 5.6240. Min Act: -0.1700
Data Index: 2102544 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7490. Min Range: -5.7490
Max Act: 5.5615. Min Act: -0.1700
Data Index: 8085541 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7490. Min Range: -5.7490
Max Act: 5.5303. Min Act: -0.1700
Data Index: 3505194 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7490. Min Range: -5.7490
Max Act: 5.5303. Min Act: -0.1700
Data Index: 4449611 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7490. Min Range: -5.7490
Max Act: 5.5303. Min Act: -0.1700
Data Index: 931635 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7490. Min Range: -5.7490
Max Act: 5.5303. Min Act: -0.1700
Data Index: 5420365 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7490. Min Range: -5.7490
Max Act: 5.5303. Min Act: -0.1700
Data Index: 6511247 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7490. Min Range: -5.7490
Max Act: 5.4990. Min Act: -0.1700
Data Index: 3434737 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7490. Min Range: -5.7490
Max Act: 5.5303. Min Act: -0.1700
Data Index: 3969804 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7490. Min Range: -5.7490
Max Act: 5.4990. Min Act: -0.1700
Data Index: 3366987 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7490. Min Range: -5.7490
Max Act: 5.4990. Min Act: -0.1700
Data Index: 2809767 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7490. Min Range: -5.7490
Max Act: 5.4678. Min Act: -0.1700
Data Index: 6751891 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7490. Min Range: -5.7490
Max Act: 5.4678. Min Act: -0.1700
Data Index: 6830771 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #19