Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1946 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 1.9439. Min Range: -1.9439
Max Act: 1.8763. Min Act: -0.0001
Data Index: 729357 (C4 (Web Text))
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.9439. Min Range: -1.9439
Max Act: 1.8388. Min Act: -0.0001
Data Index: 121714 (C4 (Web Text))
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.9439. Min Range: -1.9439
Max Act: 1.7599. Min Act: -0.0001
Data Index: 971389 (C4 (Web Text))
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.9439. Min Range: -1.9439
Max Act: 1.9439. Min Act: -0.0001
Data Index: 759481 (C4 (Web Text))
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.9439. Min Range: -1.9439
Max Act: 1.7488. Min Act: -0.0001
Data Index: 694445 (C4 (Web Text))
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.9439. Min Range: -1.9439
Max Act: 1.8385. Min Act: -0.0001
Data Index: 422862 (C4 (Web Text))
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.9439. Min Range: -1.9439
Max Act: 1.7479. Min Act: -0.0001
Data Index: 725770 (C4 (Web Text))
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.9439. Min Range: -1.9439
Max Act: 1.8223. Min Act: -0.0001
Data Index: 366920 (C4 (Web Text))
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.9439. Min Range: -1.9439
Max Act: 1.7525. Min Act: -0.0001
Data Index: 185079 (C4 (Web Text))
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.9439. Min Range: -1.9439
Max Act: 1.8067. Min Act: -0.0001
Data Index: 995264 (C4 (Web Text))
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.9439. Min Range: -1.9439
Max Act: 1.8206. Min Act: -0.0001
Data Index: 153091 (C4 (Web Text))
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.9439. Min Range: -1.9439
Max Act: 1.6024. Min Act: -0.0001
Data Index: 66435 (C4 (Web Text))
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.9439. Min Range: -1.9439
Max Act: 1.6889. Min Act: -0.0001
Data Index: 162673 (C4 (Web Text))
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.9439. Min Range: -1.9439
Max Act: 1.7656. Min Act: -0.0001
Data Index: 482081 (C4 (Web Text))
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.9439. Min Range: -1.9439
Max Act: 1.7720. Min Act: -0.0001
Data Index: 268795 (C4 (Web Text))
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.9439. Min Range: -1.9439
Max Act: 1.8570. Min Act: -0.0001
Data Index: 630917 (C4 (Web Text))
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.9439. Min Range: -1.9439
Max Act: 1.7513. Min Act: -0.0001
Data Index: 901123 (C4 (Web Text))
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.9439. Min Range: -1.9439
Max Act: 1.7276. Min Act: -0.0001
Data Index: 884554 (C4 (Web Text))
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.9439. Min Range: -1.9439
Max Act: 1.7416. Min Act: -0.0001
Data Index: 1145114 (C4 (Web Text))
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.9439. Min Range: -1.9439
Max Act: 1.5734. Min Act: -0.0001
Data Index: 720065 (C4 (Web Text))
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #19