Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1970 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 4.5851. Min Range: -4.5851
Max Act: 4.5851. Min Act: -0.0001
Data Index: 175894 (C4 (Web Text))
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5851. Min Range: -4.5851
Max Act: 4.3511. Min Act: -0.0001
Data Index: 408915 (C4 (Web Text))
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5851. Min Range: -4.5851
Max Act: 3.9411. Min Act: -0.0001
Data Index: 1274961 (C4 (Web Text))
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5851. Min Range: -4.5851
Max Act: 4.3077. Min Act: -0.0001
Data Index: 740567 (C4 (Web Text))
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5851. Min Range: -4.5851
Max Act: 3.6184. Min Act: -0.0001
Data Index: 1150861 (C4 (Web Text))
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5851. Min Range: -4.5851
Max Act: 3.7029. Min Act: -0.0001
Data Index: 586070 (C4 (Web Text))
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5851. Min Range: -4.5851
Max Act: 3.5074. Min Act: -0.0001
Data Index: 497521 (C4 (Web Text))
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5851. Min Range: -4.5851
Max Act: 3.8266. Min Act: -0.0001
Data Index: 355798 (C4 (Web Text))
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5851. Min Range: -4.5851
Max Act: 3.4864. Min Act: -0.0001
Data Index: 982353 (C4 (Web Text))
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5851. Min Range: -4.5851
Max Act: 3.3134. Min Act: -0.0001
Data Index: 916658 (C4 (Web Text))
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5851. Min Range: -4.5851
Max Act: 3.5201. Min Act: -0.0001
Data Index: 1047970 (C4 (Web Text))
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5851. Min Range: -4.5851
Max Act: 3.4798. Min Act: -0.0001
Data Index: 728768 (C4 (Web Text))
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5851. Min Range: -4.5851
Max Act: 3.5703. Min Act: -0.0001
Data Index: 1262158 (C4 (Web Text))
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5851. Min Range: -4.5851
Max Act: 3.3953. Min Act: -0.0001
Data Index: 789780 (C4 (Web Text))
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5851. Min Range: -4.5851
Max Act: 3.3442. Min Act: -0.0001
Data Index: 388047 (C4 (Web Text))
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5851. Min Range: -4.5851
Max Act: 3.1437. Min Act: -0.0001
Data Index: 486020 (C4 (Web Text))
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5851. Min Range: -4.5851
Max Act: 3.4038. Min Act: -0.0001
Data Index: 796651 (C4 (Web Text))
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5851. Min Range: -4.5851
Max Act: 3.0929. Min Act: -0.0001
Data Index: 518300 (C4 (Web Text))
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5851. Min Range: -4.5851
Max Act: 3.3661. Min Act: -0.0001
Data Index: 863841 (C4 (Web Text))
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5851. Min Range: -4.5851
Max Act: 3.1789. Min Act: -0.0001
Data Index: 720977 (C4 (Web Text))
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #19