Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3821 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 2.3492. Min Range: -2.3492
Max Act: 2.3492. Min Act: -0.0001
Data Index: 724423 (C4 (Web Text))
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.3492. Min Range: -2.3492
Max Act: 2.3104. Min Act: -0.0001
Data Index: 340324 (C4 (Web Text))
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.3492. Min Range: -2.3492
Max Act: 2.1052. Min Act: -0.0001
Data Index: 338336 (C4 (Web Text))
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.3492. Min Range: -2.3492
Max Act: 2.1228. Min Act: -0.0002
Data Index: 279283 (C4 (Web Text))
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.3492. Min Range: -2.3492
Max Act: 2.0452. Min Act: -0.0001
Data Index: 592458 (C4 (Web Text))
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.3492. Min Range: -2.3492
Max Act: 2.0351. Min Act: -0.0001
Data Index: 1133278 (C4 (Web Text))
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.3492. Min Range: -2.3492
Max Act: 2.0883. Min Act: -0.0001
Data Index: 879919 (C4 (Web Text))
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.3492. Min Range: -2.3492
Max Act: 1.9410. Min Act: -0.0001
Data Index: 434558 (C4 (Web Text))
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.3492. Min Range: -2.3492
Max Act: 1.8792. Min Act: -0.0001
Data Index: 118548 (C4 (Web Text))
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.3492. Min Range: -2.3492
Max Act: 1.9880. Min Act: -0.0001
Data Index: 185515 (C4 (Web Text))
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.3492. Min Range: -2.3492
Max Act: 1.8952. Min Act: -0.0002
Data Index: 27405 (C4 (Web Text))
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.3492. Min Range: -2.3492
Max Act: 1.9375. Min Act: -0.0001
Data Index: 223967 (C4 (Web Text))
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.3492. Min Range: -2.3492
Max Act: 1.9102. Min Act: -0.0001
Data Index: 1261608 (C4 (Web Text))
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.3492. Min Range: -2.3492
Max Act: 1.7398. Min Act: -0.0001
Data Index: 567160 (C4 (Web Text))
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.3492. Min Range: -2.3492
Max Act: 1.8752. Min Act: -0.0001
Data Index: 834181 (C4 (Web Text))
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.3492. Min Range: -2.3492
Max Act: 1.8933. Min Act: -0.0001
Data Index: 430957 (C4 (Web Text))
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.3492. Min Range: -2.3492
Max Act: 1.7227. Min Act: -0.0001
Data Index: 704555 (C4 (Web Text))
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.3492. Min Range: -2.3492
Max Act: 1.8357. Min Act: -0.0001
Data Index: 381891 (C4 (Web Text))
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.3492. Min Range: -2.3492
Max Act: 1.7633. Min Act: -0.0001
Data Index: 1128103 (C4 (Web Text))
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.3492. Min Range: -2.3492
Max Act: 1.7727. Min Act: -0.0001
Data Index: 199677 (C4 (Web Text))
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #19