Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3692 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 2.0837. Min Range: -2.0837
Max Act: 1.9511. Min Act: -0.0000
Data Index: 276991 (C4 (Web Text))
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.0837. Min Range: -2.0837
Max Act: 2.0837. Min Act: -0.0000
Data Index: 158655 (C4 (Web Text))
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.0837. Min Range: -2.0837
Max Act: 2.0687. Min Act: -0.0001
Data Index: 662642 (C4 (Web Text))
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.0837. Min Range: -2.0837
Max Act: 1.8680. Min Act: -0.0000
Data Index: 1090183 (C4 (Web Text))
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.0837. Min Range: -2.0837
Max Act: 1.8306. Min Act: -0.0000
Data Index: 40779 (C4 (Web Text))
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.0837. Min Range: -2.0837
Max Act: 1.7383. Min Act: -0.0001
Data Index: 1302493 (C4 (Web Text))
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.0837. Min Range: -2.0837
Max Act: 1.6242. Min Act: -0.0000
Data Index: 789444 (C4 (Web Text))
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.0837. Min Range: -2.0837
Max Act: 1.7962. Min Act: -0.0001
Data Index: 577148 (C4 (Web Text))
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.0837. Min Range: -2.0837
Max Act: 1.5600. Min Act: -0.0001
Data Index: 745659 (C4 (Web Text))
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.0837. Min Range: -2.0837
Max Act: 1.5257. Min Act: -0.0000
Data Index: 1111797 (C4 (Web Text))
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.0837. Min Range: -2.0837
Max Act: 1.4980. Min Act: -0.0001
Data Index: 681197 (C4 (Web Text))
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.0837. Min Range: -2.0837
Max Act: 1.4016. Min Act: -0.0001
Data Index: 982978 (C4 (Web Text))
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.0837. Min Range: -2.0837
Max Act: 1.5273. Min Act: -0.0001
Data Index: 368545 (C4 (Web Text))
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.0837. Min Range: -2.0837
Max Act: 1.3090. Min Act: -0.0001
Data Index: 1315823 (C4 (Web Text))
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.0837. Min Range: -2.0837
Max Act: 1.4129. Min Act: -0.0001
Data Index: 342253 (C4 (Web Text))
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.0837. Min Range: -2.0837
Max Act: 1.5777. Min Act: -0.0001
Data Index: 979433 (C4 (Web Text))
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.0837. Min Range: -2.0837
Max Act: 1.5684. Min Act: -0.0001
Data Index: 1025070 (C4 (Web Text))
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.0837. Min Range: -2.0837
Max Act: 1.4806. Min Act: -0.0001
Data Index: 137288 (C4 (Web Text))
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.0837. Min Range: -2.0837
Max Act: 1.4279. Min Act: -0.0001
Data Index: 318053 (C4 (Web Text))
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.0837. Min Range: -2.0837
Max Act: 1.3695. Min Act: -0.0001
Data Index: 249905 (C4 (Web Text))
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #19