Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5817 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 0.7517. Min Range: -0.7517
Max Act: 0.7517. Min Act: -0.1690
Data Index: 4552214 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.7517. Min Range: -0.7517
Max Act: 0.7023. Min Act: -0.1687
Data Index: 2328439 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.7517. Min Range: -0.7517
Max Act: 0.5981. Min Act: -0.1700
Data Index: 1496231 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.7517. Min Range: -0.7517
Max Act: 0.5437. Min Act: -0.1689
Data Index: 1365569 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.7517. Min Range: -0.7517
Max Act: 0.5284. Min Act: -0.1700
Data Index: 2304140 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.7517. Min Range: -0.7517
Max Act: 0.5056. Min Act: -0.1682
Data Index: 5998235 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.7517. Min Range: -0.7517
Max Act: 0.5056. Min Act: -0.1697
Data Index: 6708691 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.7517. Min Range: -0.7517
Max Act: 0.5056. Min Act: -0.1694
Data Index: 2972385 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.7517. Min Range: -0.7517
Max Act: 0.4832. Min Act: -0.1692
Data Index: 8242034 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.7517. Min Range: -0.7517
Max Act: 0.4758. Min Act: -0.1696
Data Index: 3978057 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.7517. Min Range: -0.7517
Max Act: 0.4684. Min Act: -0.1699
Data Index: 3999668 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.7517. Min Range: -0.7517
Max Act: 0.4610. Min Act: -0.1697
Data Index: 7714695 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.7517. Min Range: -0.7517
Max Act: 0.4610. Min Act: -0.1470
Data Index: 684385 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.7517. Min Range: -0.7517
Max Act: 0.4537. Min Act: -0.1674
Data Index: 8074601 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.7517. Min Range: -0.7517
Max Act: 0.4610. Min Act: -0.1666
Data Index: 485418 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.7517. Min Range: -0.7517
Max Act: 0.4537. Min Act: -0.1700
Data Index: 459290 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.7517. Min Range: -0.7517
Max Act: 0.4537. Min Act: -0.1696
Data Index: 7176521 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.7517. Min Range: -0.7517
Max Act: 0.4464. Min Act: -0.1688
Data Index: 2322814 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.7517. Min Range: -0.7517
Max Act: 0.4464. Min Act: -0.1698
Data Index: 5972898 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.7517. Min Range: -0.7517
Max Act: 0.4391. Min Act: -0.1690
Data Index: 2802539 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #19