Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1338 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 2.9121. Min Range: -2.9121
Max Act: 2.9121. Min Act: -0.1700
Data Index: 392287 (C4 (Web Text))
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9121. Min Range: -2.9121
Max Act: 2.8803. Min Act: -0.1700
Data Index: 1034672 (C4 (Web Text))
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9121. Min Range: -2.9121
Max Act: 2.8486. Min Act: -0.1700
Data Index: 329410 (C4 (Web Text))
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9121. Min Range: -2.9121
Max Act: 2.8644. Min Act: -0.1700
Data Index: 793195 (C4 (Web Text))
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9121. Min Range: -2.9121
Max Act: 2.8167. Min Act: -0.1700
Data Index: 876840 (C4 (Web Text))
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9121. Min Range: -2.9121
Max Act: 2.8327. Min Act: -0.1700
Data Index: 716915 (C4 (Web Text))
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9121. Min Range: -2.9121
Max Act: 2.8327. Min Act: -0.1700
Data Index: 375298 (C4 (Web Text))
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9121. Min Range: -2.9121
Max Act: 2.8167. Min Act: -0.1700
Data Index: 241260 (C4 (Web Text))
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9121. Min Range: -2.9121
Max Act: 2.7849. Min Act: -0.1700
Data Index: 676272 (C4 (Web Text))
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9121. Min Range: -2.9121
Max Act: 2.8008. Min Act: -0.1700
Data Index: 826075 (C4 (Web Text))
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9121. Min Range: -2.9121
Max Act: 2.7849. Min Act: -0.1700
Data Index: 124899 (C4 (Web Text))
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9121. Min Range: -2.9121
Max Act: 2.7690. Min Act: -0.1700
Data Index: 281150 (C4 (Web Text))
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9121. Min Range: -2.9121
Max Act: 2.7370. Min Act: -0.1700
Data Index: 706659 (C4 (Web Text))
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9121. Min Range: -2.9121
Max Act: 2.7690. Min Act: -0.1700
Data Index: 892781 (C4 (Web Text))
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9121. Min Range: -2.9121
Max Act: 2.7530. Min Act: -0.1700
Data Index: 42359 (C4 (Web Text))
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9121. Min Range: -2.9121
Max Act: 2.7530. Min Act: -0.1700
Data Index: 483446 (C4 (Web Text))
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9121. Min Range: -2.9121
Max Act: 2.7530. Min Act: -0.1700
Data Index: 1079518 (C4 (Web Text))
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9121. Min Range: -2.9121
Max Act: 2.7370. Min Act: -0.1700
Data Index: 641646 (C4 (Web Text))
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9121. Min Range: -2.9121
Max Act: 2.7849. Min Act: -0.1700
Data Index: 1236638 (C4 (Web Text))
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9121. Min Range: -2.9121
Max Act: 2.7211. Min Act: -0.1700
Data Index: 790334 (C4 (Web Text))
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #19