Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3255 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 2.8453. Min Range: -2.8453
Max Act: 2.8453. Min Act: -0.0001
Data Index: 758140 (C4 (Web Text))
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8453. Min Range: -2.8453
Max Act: 2.5966. Min Act: -0.0001
Data Index: 212489 (C4 (Web Text))
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8453. Min Range: -2.8453
Max Act: 2.3817. Min Act: -0.0001
Data Index: 1100942 (C4 (Web Text))
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8453. Min Range: -2.8453
Max Act: 2.4976. Min Act: -0.0001
Data Index: 652161 (C4 (Web Text))
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8453. Min Range: -2.8453
Max Act: 2.4568. Min Act: -0.0001
Data Index: 1300468 (C4 (Web Text))
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8453. Min Range: -2.8453
Max Act: 2.5410. Min Act: -0.0001
Data Index: 398779 (C4 (Web Text))
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8453. Min Range: -2.8453
Max Act: 2.3020. Min Act: -0.0001
Data Index: 1102045 (C4 (Web Text))
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8453. Min Range: -2.8453
Max Act: 2.5314. Min Act: -0.0001
Data Index: 647643 (C4 (Web Text))
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8453. Min Range: -2.8453
Max Act: 2.2703. Min Act: -0.0001
Data Index: 1197198 (C4 (Web Text))
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8453. Min Range: -2.8453
Max Act: 2.4022. Min Act: -0.0001
Data Index: 561807 (C4 (Web Text))
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8453. Min Range: -2.8453
Max Act: 2.5321. Min Act: -0.0001
Data Index: 476425 (C4 (Web Text))
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8453. Min Range: -2.8453
Max Act: 2.3552. Min Act: -0.0001
Data Index: 500715 (C4 (Web Text))
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8453. Min Range: -2.8453
Max Act: 2.3452. Min Act: -0.0001
Data Index: 57215 (C4 (Web Text))
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8453. Min Range: -2.8453
Max Act: 2.2173. Min Act: -0.0001
Data Index: 949551 (C4 (Web Text))
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8453. Min Range: -2.8453
Max Act: 2.1887. Min Act: -0.0001
Data Index: 613962 (C4 (Web Text))
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8453. Min Range: -2.8453
Max Act: 2.3110. Min Act: -0.0001
Data Index: 161576 (C4 (Web Text))
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8453. Min Range: -2.8453
Max Act: 2.0867. Min Act: -0.0001
Data Index: 803615 (C4 (Web Text))
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8453. Min Range: -2.8453
Max Act: 2.3922. Min Act: -0.0001
Data Index: 525406 (C4 (Web Text))
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8453. Min Range: -2.8453
Max Act: 2.3743. Min Act: -0.0001
Data Index: 410285 (C4 (Web Text))
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8453. Min Range: -2.8453
Max Act: 2.4002. Min Act: -0.0001
Data Index: 706878 (C4 (Web Text))
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #19