Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 686 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 2.2849. Min Range: -2.2849
Max Act: 2.2849. Min Act: -0.0001
Data Index: 387943 (C4 (Web Text))
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.2849. Min Range: -2.2849
Max Act: 2.2700. Min Act: -0.0002
Data Index: 350478 (C4 (Web Text))
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.2849. Min Range: -2.2849
Max Act: 2.2494. Min Act: -0.0001
Data Index: 410855 (C4 (Web Text))
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.2849. Min Range: -2.2849
Max Act: 1.9795. Min Act: -0.0001
Data Index: 433489 (C4 (Web Text))
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.2849. Min Range: -2.2849
Max Act: 2.1771. Min Act: -0.0002
Data Index: 443518 (C4 (Web Text))
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.2849. Min Range: -2.2849
Max Act: 2.0708. Min Act: -0.0001
Data Index: 85274 (C4 (Web Text))
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.2849. Min Range: -2.2849
Max Act: 2.1609. Min Act: -0.0002
Data Index: 1346526 (C4 (Web Text))
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.2849. Min Range: -2.2849
Max Act: 1.9219. Min Act: -0.0001
Data Index: 508086 (C4 (Web Text))
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.2849. Min Range: -2.2849
Max Act: 2.0412. Min Act: -0.0002
Data Index: 1100021 (C4 (Web Text))
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.2849. Min Range: -2.2849
Max Act: 1.9807. Min Act: -0.0002
Data Index: 547222 (C4 (Web Text))
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.2849. Min Range: -2.2849
Max Act: 1.8797. Min Act: -0.0002
Data Index: 43190 (C4 (Web Text))
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.2849. Min Range: -2.2849
Max Act: 1.9978. Min Act: -0.0002
Data Index: 1004897 (C4 (Web Text))
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.2849. Min Range: -2.2849
Max Act: 1.8355. Min Act: -0.0002
Data Index: 403680 (C4 (Web Text))
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.2849. Min Range: -2.2849
Max Act: 1.9389. Min Act: -0.0002
Data Index: 1274158 (C4 (Web Text))
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.2849. Min Range: -2.2849
Max Act: 1.9090. Min Act: -0.0002
Data Index: 1129573 (C4 (Web Text))
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.2849. Min Range: -2.2849
Max Act: 1.8228. Min Act: -0.0002
Data Index: 1240163 (C4 (Web Text))
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.2849. Min Range: -2.2849
Max Act: 1.7616. Min Act: -0.0002
Data Index: 711570 (C4 (Web Text))
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.2849. Min Range: -2.2849
Max Act: 1.9141. Min Act: -0.0001
Data Index: 563289 (C4 (Web Text))
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.2849. Min Range: -2.2849
Max Act: 1.9710. Min Act: -0.0001
Data Index: 701541 (C4 (Web Text))
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.2849. Min Range: -2.2849
Max Act: 1.8916. Min Act: -0.0002
Data Index: 401285 (C4 (Web Text))
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #19