Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3700 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 1.4679. Min Range: -1.4679
Max Act: 1.3280. Min Act: -0.0001
Data Index: 142378 (C4 (Web Text))
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.4679. Min Range: -1.4679
Max Act: 1.1795. Min Act: -0.0001
Data Index: 789278 (C4 (Web Text))
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.4679. Min Range: -1.4679
Max Act: 1.4679. Min Act: -0.0001
Data Index: 159207 (C4 (Web Text))
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.4679. Min Range: -1.4679
Max Act: 1.4014. Min Act: -0.0001
Data Index: 793873 (C4 (Web Text))
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.4679. Min Range: -1.4679
Max Act: 1.1604. Min Act: -0.0001
Data Index: 1011579 (C4 (Web Text))
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.4679. Min Range: -1.4679
Max Act: 1.3765. Min Act: -0.0001
Data Index: 686314 (C4 (Web Text))
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.4679. Min Range: -1.4679
Max Act: 1.3772. Min Act: -0.0001
Data Index: 1240097 (C4 (Web Text))
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.4679. Min Range: -1.4679
Max Act: 1.2937. Min Act: -0.0001
Data Index: 895410 (C4 (Web Text))
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.4679. Min Range: -1.4679
Max Act: 1.3104. Min Act: -0.0001
Data Index: 714991 (C4 (Web Text))
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.4679. Min Range: -1.4679
Max Act: 1.3463. Min Act: -0.0001
Data Index: 857485 (C4 (Web Text))
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.4679. Min Range: -1.4679
Max Act: 1.2587. Min Act: -0.0001
Data Index: 1138954 (C4 (Web Text))
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.4679. Min Range: -1.4679
Max Act: 1.2567. Min Act: -0.0001
Data Index: 685256 (C4 (Web Text))
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.4679. Min Range: -1.4679
Max Act: 1.2895. Min Act: -0.0001
Data Index: 611393 (C4 (Web Text))
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.4679. Min Range: -1.4679
Max Act: 1.2128. Min Act: -0.0001
Data Index: 861692 (C4 (Web Text))
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.4679. Min Range: -1.4679
Max Act: 1.1809. Min Act: -0.0001
Data Index: 341294 (C4 (Web Text))
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.4679. Min Range: -1.4679
Max Act: 1.2382. Min Act: -0.0001
Data Index: 1238513 (C4 (Web Text))
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.4679. Min Range: -1.4679
Max Act: 1.2369. Min Act: -0.0001
Data Index: 978910 (C4 (Web Text))
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.4679. Min Range: -1.4679
Max Act: 1.1466. Min Act: -0.0001
Data Index: 1340353 (C4 (Web Text))
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.4679. Min Range: -1.4679
Max Act: 1.2801. Min Act: -0.0001
Data Index: 784415 (C4 (Web Text))
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.4679. Min Range: -1.4679
Max Act: 1.1682. Min Act: -0.0001
Data Index: 1001021 (C4 (Web Text))
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #19