Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 873 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 2.4903. Min Range: -2.4903
Max Act: 2.4903. Min Act: -0.1700
Data Index: 21401 (C4 (Web Text))
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.4903. Min Range: -2.4903
Max Act: 2.4416. Min Act: -0.1700
Data Index: 679381 (C4 (Web Text))
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.4903. Min Range: -2.4903
Max Act: 2.4416. Min Act: -0.1700
Data Index: 377780 (C4 (Web Text))
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.4903. Min Range: -2.4903
Max Act: 2.4416. Min Act: -0.1700
Data Index: 407800 (C4 (Web Text))
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.4903. Min Range: -2.4903
Max Act: 2.4416. Min Act: -0.1700
Data Index: 1061256 (C4 (Web Text))
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.4903. Min Range: -2.4903
Max Act: 2.4253. Min Act: -0.1700
Data Index: 592299 (C4 (Web Text))
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.4903. Min Range: -2.4903
Max Act: 2.4253. Min Act: -0.1700
Data Index: 1038596 (C4 (Web Text))
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.4903. Min Range: -2.4903
Max Act: 2.4090. Min Act: -0.1700
Data Index: 1324286 (C4 (Web Text))
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.4903. Min Range: -2.4903
Max Act: 2.4090. Min Act: -0.1700
Data Index: 146012 (C4 (Web Text))
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.4903. Min Range: -2.4903
Max Act: 2.4090. Min Act: -0.1700
Data Index: 1070869 (C4 (Web Text))
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.4903. Min Range: -2.4903
Max Act: 2.4090. Min Act: -0.1700
Data Index: 114020 (C4 (Web Text))
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.4903. Min Range: -2.4903
Max Act: 2.4090. Min Act: -0.1700
Data Index: 281448 (C4 (Web Text))
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.4903. Min Range: -2.4903
Max Act: 2.3927. Min Act: -0.1700
Data Index: 1019677 (C4 (Web Text))
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.4903. Min Range: -2.4903
Max Act: 2.3927. Min Act: -0.1700
Data Index: 967600 (C4 (Web Text))
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.4903. Min Range: -2.4903
Max Act: 2.3927. Min Act: -0.1700
Data Index: 869564 (C4 (Web Text))
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.4903. Min Range: -2.4903
Max Act: 2.3764. Min Act: -0.1700
Data Index: 886258 (C4 (Web Text))
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.4903. Min Range: -2.4903
Max Act: 2.3764. Min Act: -0.1700
Data Index: 290174 (C4 (Web Text))
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.4903. Min Range: -2.4903
Max Act: 2.3600. Min Act: -0.1700
Data Index: 153150 (C4 (Web Text))
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.4903. Min Range: -2.4903
Max Act: 2.3764. Min Act: -0.1700
Data Index: 1075655 (C4 (Web Text))
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.4903. Min Range: -2.4903
Max Act: 2.3764. Min Act: -0.1700
Data Index: 833077 (C4 (Web Text))
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #19