Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3552 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 2.9437. Min Range: -2.9437
Max Act: 2.9437. Min Act: -0.0001
Data Index: 1041597 (C4 (Web Text))
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9437. Min Range: -2.9437
Max Act: 2.7358. Min Act: -0.0001
Data Index: 475742 (C4 (Web Text))
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9437. Min Range: -2.9437
Max Act: 2.5438. Min Act: -0.0001
Data Index: 670780 (C4 (Web Text))
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9437. Min Range: -2.9437
Max Act: 2.4813. Min Act: -0.0001
Data Index: 424106 (C4 (Web Text))
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9437. Min Range: -2.9437
Max Act: 2.4795. Min Act: -0.0001
Data Index: 449191 (C4 (Web Text))
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9437. Min Range: -2.9437
Max Act: 2.5090. Min Act: -0.0001
Data Index: 1277655 (C4 (Web Text))
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9437. Min Range: -2.9437
Max Act: 2.5041. Min Act: -0.0000
Data Index: 324365 (C4 (Web Text))
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9437. Min Range: -2.9437
Max Act: 2.3845. Min Act: -0.0001
Data Index: 22182 (C4 (Web Text))
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9437. Min Range: -2.9437
Max Act: 2.3505. Min Act: -0.0001
Data Index: 729171 (C4 (Web Text))
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9437. Min Range: -2.9437
Max Act: 2.4124. Min Act: -0.0000
Data Index: 71435 (C4 (Web Text))
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9437. Min Range: -2.9437
Max Act: 2.1702. Min Act: -0.0001
Data Index: 1282335 (C4 (Web Text))
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9437. Min Range: -2.9437
Max Act: 2.1612. Min Act: -0.0001
Data Index: 826685 (C4 (Web Text))
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9437. Min Range: -2.9437
Max Act: 2.3922. Min Act: -0.0000
Data Index: 1038575 (C4 (Web Text))
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9437. Min Range: -2.9437
Max Act: 2.2644. Min Act: -0.0001
Data Index: 267690 (C4 (Web Text))
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9437. Min Range: -2.9437
Max Act: 2.1443. Min Act: -0.0001
Data Index: 360533 (C4 (Web Text))
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9437. Min Range: -2.9437
Max Act: 2.4777. Min Act: -0.0001
Data Index: 977937 (C4 (Web Text))
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9437. Min Range: -2.9437
Max Act: 2.2346. Min Act: -0.0001
Data Index: 221095 (C4 (Web Text))
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9437. Min Range: -2.9437
Max Act: 2.2377. Min Act: -0.0001
Data Index: 59216 (C4 (Web Text))
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9437. Min Range: -2.9437
Max Act: 2.1118. Min Act: -0.0000
Data Index: 1085810 (C4 (Web Text))
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9437. Min Range: -2.9437
Max Act: 2.2204. Min Act: -0.0000
Data Index: 1053092 (C4 (Web Text))
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #19