Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4190 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8351. Min Range: -6.8351
Max Act: 6.8351. Min Act: -0.1700
Data Index: 7679313 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8351. Min Range: -6.8351
Max Act: 6.5851. Min Act: -0.1700
Data Index: 8237426 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8351. Min Range: -6.8351
Max Act: 6.4601. Min Act: -0.1700
Data Index: 5705727 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8351. Min Range: -6.8351
Max Act: 6.3351. Min Act: -0.1700
Data Index: 6706894 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8351. Min Range: -6.8351
Max Act: 6.3039. Min Act: -0.1700
Data Index: 1026522 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8351. Min Range: -6.8351
Max Act: 6.1789. Min Act: -0.1700
Data Index: 6077230 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8351. Min Range: -6.8351
Max Act: 6.0851. Min Act: -0.1700
Data Index: 309700 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8351. Min Range: -6.8351
Max Act: 6.0539. Min Act: -0.1700
Data Index: 3979765 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8351. Min Range: -6.8351
Max Act: 5.9914. Min Act: -0.1700
Data Index: 4688309 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8351. Min Range: -6.8351
Max Act: 5.9601. Min Act: -0.1700
Data Index: 2865102 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8351. Min Range: -6.8351
Max Act: 5.9601. Min Act: -0.1700
Data Index: 3720444 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8351. Min Range: -6.8351
Max Act: 5.9289. Min Act: -0.1700
Data Index: 6756483 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8351. Min Range: -6.8351
Max Act: 5.9601. Min Act: -0.1700
Data Index: 4826451 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8351. Min Range: -6.8351
Max Act: 5.9289. Min Act: -0.1700
Data Index: 701092 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8351. Min Range: -6.8351
Max Act: 5.9289. Min Act: -0.1700
Data Index: 4898154 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8351. Min Range: -6.8351
Max Act: 5.9601. Min Act: -0.1700
Data Index: 7324327 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8351. Min Range: -6.8351
Max Act: 5.9289. Min Act: -0.1700
Data Index: 7713870 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8351. Min Range: -6.8351
Max Act: 5.9289. Min Act: -0.1700
Data Index: 8231909 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8351. Min Range: -6.8351
Max Act: 5.8976. Min Act: -0.1700
Data Index: 5751037 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8351. Min Range: -6.8351
Max Act: 5.8976. Min Act: -0.1700
Data Index: 5569921 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #19