Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2471 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 4.4914. Min Range: -4.4914
Max Act: 4.4914. Min Act: -0.0001
Data Index: 643727 (C4 (Web Text))
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4914. Min Range: -4.4914
Max Act: 3.9156. Min Act: -0.0001
Data Index: 699036 (C4 (Web Text))
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4914. Min Range: -4.4914
Max Act: 3.8304. Min Act: -0.0001
Data Index: 787330 (C4 (Web Text))
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4914. Min Range: -4.4914
Max Act: 3.1094. Min Act: -0.0001
Data Index: 735313 (C4 (Web Text))
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4914. Min Range: -4.4914
Max Act: 2.9024. Min Act: -0.0001
Data Index: 603575 (C4 (Web Text))
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4914. Min Range: -4.4914
Max Act: 2.6377. Min Act: -0.0001
Data Index: 463028 (C4 (Web Text))
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4914. Min Range: -4.4914
Max Act: 2.4498. Min Act: -0.0001
Data Index: 63981 (C4 (Web Text))
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4914. Min Range: -4.4914
Max Act: 2.5212. Min Act: -0.0001
Data Index: 291164 (C4 (Web Text))
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4914. Min Range: -4.4914
Max Act: 2.4861. Min Act: -0.0001
Data Index: 156245 (C4 (Web Text))
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4914. Min Range: -4.4914
Max Act: 2.4068. Min Act: -0.0001
Data Index: 1270467 (C4 (Web Text))
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4914. Min Range: -4.4914
Max Act: 2.2406. Min Act: -0.0001
Data Index: 45458 (C4 (Web Text))
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4914. Min Range: -4.4914
Max Act: 2.3496. Min Act: -0.0001
Data Index: 368339 (C4 (Web Text))
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4914. Min Range: -4.4914
Max Act: 2.2826. Min Act: -0.0001
Data Index: 1093907 (C4 (Web Text))
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4914. Min Range: -4.4914
Max Act: 2.1569. Min Act: -0.0001
Data Index: 1125212 (C4 (Web Text))
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4914. Min Range: -4.4914
Max Act: 2.3835. Min Act: -0.0001
Data Index: 294856 (C4 (Web Text))
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4914. Min Range: -4.4914
Max Act: 2.2486. Min Act: -0.0001
Data Index: 139674 (C4 (Web Text))
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4914. Min Range: -4.4914
Max Act: 2.2371. Min Act: -0.0001
Data Index: 1213368 (C4 (Web Text))
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4914. Min Range: -4.4914
Max Act: 2.2294. Min Act: -0.0001
Data Index: 614633 (C4 (Web Text))
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4914. Min Range: -4.4914
Max Act: 2.2031. Min Act: -0.0001
Data Index: 97108 (C4 (Web Text))
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4914. Min Range: -4.4914
Max Act: 2.1969. Min Act: -0.0001
Data Index: 585323 (C4 (Web Text))
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #19