Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2457 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 2.9594. Min Range: -2.9594
Max Act: 2.9594. Min Act: -0.0001
Data Index: 650687 (C4 (Web Text))
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9594. Min Range: -2.9594
Max Act: 2.7124. Min Act: -0.0001
Data Index: 663591 (C4 (Web Text))
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9594. Min Range: -2.9594
Max Act: 2.6681. Min Act: -0.0001
Data Index: 1002243 (C4 (Web Text))
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9594. Min Range: -2.9594
Max Act: 2.7561. Min Act: -0.0001
Data Index: 411157 (C4 (Web Text))
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9594. Min Range: -2.9594
Max Act: 2.3145. Min Act: -0.0001
Data Index: 1219198 (C4 (Web Text))
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9594. Min Range: -2.9594
Max Act: 2.4059. Min Act: -0.0001
Data Index: 715555 (C4 (Web Text))
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9594. Min Range: -2.9594
Max Act: 2.2153. Min Act: -0.0001
Data Index: 1047164 (C4 (Web Text))
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9594. Min Range: -2.9594
Max Act: 2.3276. Min Act: -0.0001
Data Index: 274205 (C4 (Web Text))
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9594. Min Range: -2.9594
Max Act: 2.1815. Min Act: -0.0001
Data Index: 256417 (C4 (Web Text))
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9594. Min Range: -2.9594
Max Act: 2.3886. Min Act: -0.0001
Data Index: 813563 (C4 (Web Text))
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9594. Min Range: -2.9594
Max Act: 2.2870. Min Act: -0.0001
Data Index: 108402 (C4 (Web Text))
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9594. Min Range: -2.9594
Max Act: 2.3017. Min Act: -0.0001
Data Index: 958797 (C4 (Web Text))
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9594. Min Range: -2.9594
Max Act: 2.4319. Min Act: -0.0001
Data Index: 1359668 (C4 (Web Text))
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9594. Min Range: -2.9594
Max Act: 2.2842. Min Act: -0.0001
Data Index: 714672 (C4 (Web Text))
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9594. Min Range: -2.9594
Max Act: 2.2620. Min Act: -0.0001
Data Index: 259839 (C4 (Web Text))
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9594. Min Range: -2.9594
Max Act: 2.2652. Min Act: -0.0001
Data Index: 765927 (C4 (Web Text))
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9594. Min Range: -2.9594
Max Act: 2.3708. Min Act: -0.0001
Data Index: 992508 (C4 (Web Text))
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9594. Min Range: -2.9594
Max Act: 2.2659. Min Act: -0.0001
Data Index: 383805 (C4 (Web Text))
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9594. Min Range: -2.9594
Max Act: 2.1611. Min Act: -0.0001
Data Index: 1030957 (C4 (Web Text))
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9594. Min Range: -2.9594
Max Act: 2.0570. Min Act: -0.0001
Data Index: 615359 (C4 (Web Text))
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #19