Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 45 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 2.7196. Min Range: -2.7196
Max Act: 2.7196. Min Act: -0.0001
Data Index: 139457 (C4 (Web Text))
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7196. Min Range: -2.7196
Max Act: 2.3692. Min Act: -0.0001
Data Index: 327252 (C4 (Web Text))
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7196. Min Range: -2.7196
Max Act: 2.1538. Min Act: -0.0001
Data Index: 774161 (C4 (Web Text))
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7196. Min Range: -2.7196
Max Act: 2.2628. Min Act: -0.0001
Data Index: 1167120 (C4 (Web Text))
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7196. Min Range: -2.7196
Max Act: 2.1474. Min Act: -0.0001
Data Index: 1228802 (C4 (Web Text))
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7196. Min Range: -2.7196
Max Act: 2.0799. Min Act: -0.0001
Data Index: 46590 (C4 (Web Text))
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7196. Min Range: -2.7196
Max Act: 2.2038. Min Act: -0.0001
Data Index: 505140 (C4 (Web Text))
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7196. Min Range: -2.7196
Max Act: 2.0963. Min Act: -0.0001
Data Index: 1007458 (C4 (Web Text))
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7196. Min Range: -2.7196
Max Act: 2.1023. Min Act: -0.0001
Data Index: 819326 (C4 (Web Text))
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7196. Min Range: -2.7196
Max Act: 2.0932. Min Act: -0.0001
Data Index: 373989 (C4 (Web Text))
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7196. Min Range: -2.7196
Max Act: 2.1716. Min Act: -0.0001
Data Index: 581110 (C4 (Web Text))
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7196. Min Range: -2.7196
Max Act: 1.9598. Min Act: -0.0001
Data Index: 854187 (C4 (Web Text))
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7196. Min Range: -2.7196
Max Act: 2.1349. Min Act: -0.0001
Data Index: 1302443 (C4 (Web Text))
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7196. Min Range: -2.7196
Max Act: 2.0356. Min Act: -0.0001
Data Index: 801120 (C4 (Web Text))
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7196. Min Range: -2.7196
Max Act: 2.0318. Min Act: -0.0001
Data Index: 329076 (C4 (Web Text))
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7196. Min Range: -2.7196
Max Act: 2.0291. Min Act: -0.0001
Data Index: 1189510 (C4 (Web Text))
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7196. Min Range: -2.7196
Max Act: 1.9961. Min Act: -0.0001
Data Index: 1306819 (C4 (Web Text))
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7196. Min Range: -2.7196
Max Act: 1.9846. Min Act: -0.0001
Data Index: 1116011 (C4 (Web Text))
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7196. Min Range: -2.7196
Max Act: 2.0126. Min Act: -0.0001
Data Index: 525043 (C4 (Web Text))
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7196. Min Range: -2.7196
Max Act: 2.0829. Min Act: -0.0001
Data Index: 744438 (C4 (Web Text))
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #19