Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3504 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 4.6238. Min Range: -4.6238
Max Act: 4.6238. Min Act: -0.0001
Data Index: 1226364 (C4 (Web Text))
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6238. Min Range: -4.6238
Max Act: 4.0972. Min Act: -0.0001
Data Index: 752209 (C4 (Web Text))
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6238. Min Range: -4.6238
Max Act: 3.8708. Min Act: -0.0001
Data Index: 450635 (C4 (Web Text))
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6238. Min Range: -4.6238
Max Act: 3.9323. Min Act: -0.0001
Data Index: 1007600 (C4 (Web Text))
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6238. Min Range: -4.6238
Max Act: 3.7727. Min Act: -0.0001
Data Index: 253502 (C4 (Web Text))
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6238. Min Range: -4.6238
Max Act: 3.2734. Min Act: -0.0001
Data Index: 40494 (C4 (Web Text))
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6238. Min Range: -4.6238
Max Act: 3.7125. Min Act: -0.0001
Data Index: 1214398 (C4 (Web Text))
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6238. Min Range: -4.6238
Max Act: 3.3615. Min Act: -0.0001
Data Index: 1339632 (C4 (Web Text))
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6238. Min Range: -4.6238
Max Act: 3.4818. Min Act: -0.0001
Data Index: 861181 (C4 (Web Text))
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6238. Min Range: -4.6238
Max Act: 3.2577. Min Act: -0.0001
Data Index: 981514 (C4 (Web Text))
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6238. Min Range: -4.6238
Max Act: 3.1662. Min Act: -0.0001
Data Index: 739280 (C4 (Web Text))
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6238. Min Range: -4.6238
Max Act: 2.9999. Min Act: -0.0001
Data Index: 1345322 (C4 (Web Text))
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6238. Min Range: -4.6238
Max Act: 3.1159. Min Act: -0.0001
Data Index: 1087115 (C4 (Web Text))
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6238. Min Range: -4.6238
Max Act: 2.8655. Min Act: -0.0001
Data Index: 758951 (C4 (Web Text))
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6238. Min Range: -4.6238
Max Act: 3.2639. Min Act: -0.0001
Data Index: 589649 (C4 (Web Text))
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6238. Min Range: -4.6238
Max Act: 2.6874. Min Act: -0.0001
Data Index: 43055 (C4 (Web Text))
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6238. Min Range: -4.6238
Max Act: 3.0888. Min Act: -0.0001
Data Index: 1296488 (C4 (Web Text))
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6238. Min Range: -4.6238
Max Act: 2.9254. Min Act: -0.0001
Data Index: 48584 (C4 (Web Text))
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6238. Min Range: -4.6238
Max Act: 2.5892. Min Act: -0.0001
Data Index: 48570 (C4 (Web Text))
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6238. Min Range: -4.6238
Max Act: 2.7235. Min Act: -0.0001
Data Index: 540354 (C4 (Web Text))
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #19