Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1462 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 2.3324. Min Range: -2.3324
Max Act: 2.3324. Min Act: -0.0002
Data Index: 835923 (C4 (Web Text))
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.3324. Min Range: -2.3324
Max Act: 2.3237. Min Act: -0.0001
Data Index: 1170728 (C4 (Web Text))
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.3324. Min Range: -2.3324
Max Act: 1.9530. Min Act: -0.0001
Data Index: 855729 (C4 (Web Text))
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.3324. Min Range: -2.3324
Max Act: 1.9844. Min Act: -0.0001
Data Index: 720942 (C4 (Web Text))
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.3324. Min Range: -2.3324
Max Act: 1.8616. Min Act: -0.0001
Data Index: 1040930 (C4 (Web Text))
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.3324. Min Range: -2.3324
Max Act: 2.0236. Min Act: -0.0002
Data Index: 1270843 (C4 (Web Text))
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.3324. Min Range: -2.3324
Max Act: 1.8703. Min Act: -0.0001
Data Index: 399548 (C4 (Web Text))
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.3324. Min Range: -2.3324
Max Act: 2.0323. Min Act: -0.0001
Data Index: 121388 (C4 (Web Text))
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.3324. Min Range: -2.3324
Max Act: 1.6980. Min Act: -0.0002
Data Index: 1328402 (C4 (Web Text))
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.3324. Min Range: -2.3324
Max Act: 1.8681. Min Act: -0.0001
Data Index: 792127 (C4 (Web Text))
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.3324. Min Range: -2.3324
Max Act: 1.8731. Min Act: -0.0002
Data Index: 1259917 (C4 (Web Text))
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.3324. Min Range: -2.3324
Max Act: 1.8204. Min Act: -0.0001
Data Index: 1017399 (C4 (Web Text))
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.3324. Min Range: -2.3324
Max Act: 1.8206. Min Act: -0.0001
Data Index: 205304 (C4 (Web Text))
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.3324. Min Range: -2.3324
Max Act: 1.9005. Min Act: -0.0001
Data Index: 677702 (C4 (Web Text))
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.3324. Min Range: -2.3324
Max Act: 1.6691. Min Act: -0.0001
Data Index: 739385 (C4 (Web Text))
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.3324. Min Range: -2.3324
Max Act: 1.8171. Min Act: -0.0002
Data Index: 1300693 (C4 (Web Text))
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.3324. Min Range: -2.3324
Max Act: 1.5425. Min Act: -0.0002
Data Index: 735269 (C4 (Web Text))
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.3324. Min Range: -2.3324
Max Act: 1.7905. Min Act: -0.0002
Data Index: 668951 (C4 (Web Text))
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.3324. Min Range: -2.3324
Max Act: 1.7538. Min Act: -0.0001
Data Index: 295626 (C4 (Web Text))
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.3324. Min Range: -2.3324
Max Act: 1.6844. Min Act: -0.0002
Data Index: 342463 (C4 (Web Text))
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #19