Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 4340 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 2.5004. Min Range: -2.5004
Max Act: 2.5004. Min Act: -0.0001
Data Index: 296533 (C4 (Web Text))
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5004. Min Range: -2.5004
Max Act: 2.3628. Min Act: -0.0001
Data Index: 870667 (C4 (Web Text))
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5004. Min Range: -2.5004
Max Act: 2.0658. Min Act: -0.0001
Data Index: 500381 (C4 (Web Text))
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5004. Min Range: -2.5004
Max Act: 2.1864. Min Act: -0.0001
Data Index: 1008517 (C4 (Web Text))
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5004. Min Range: -2.5004
Max Act: 2.2778. Min Act: -0.0001
Data Index: 245780 (C4 (Web Text))
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5004. Min Range: -2.5004
Max Act: 2.1925. Min Act: -0.0001
Data Index: 210744 (C4 (Web Text))
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5004. Min Range: -2.5004
Max Act: 2.0677. Min Act: -0.0001
Data Index: 1303520 (C4 (Web Text))
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5004. Min Range: -2.5004
Max Act: 2.0734. Min Act: -0.0001
Data Index: 425567 (C4 (Web Text))
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5004. Min Range: -2.5004
Max Act: 1.9567. Min Act: -0.0001
Data Index: 24154 (C4 (Web Text))
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5004. Min Range: -2.5004
Max Act: 2.0439. Min Act: -0.0001
Data Index: 685034 (C4 (Web Text))
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5004. Min Range: -2.5004
Max Act: 1.9468. Min Act: -0.0001
Data Index: 624891 (C4 (Web Text))
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5004. Min Range: -2.5004
Max Act: 2.0512. Min Act: -0.0001
Data Index: 543282 (C4 (Web Text))
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5004. Min Range: -2.5004
Max Act: 2.0492. Min Act: -0.0001
Data Index: 1006382 (C4 (Web Text))
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5004. Min Range: -2.5004
Max Act: 1.9312. Min Act: -0.0001
Data Index: 1093089 (C4 (Web Text))
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5004. Min Range: -2.5004
Max Act: 2.2886. Min Act: -0.0001
Data Index: 1081732 (C4 (Web Text))
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5004. Min Range: -2.5004
Max Act: 2.0325. Min Act: -0.0001
Data Index: 657975 (C4 (Web Text))
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5004. Min Range: -2.5004
Max Act: 1.9667. Min Act: -0.0001
Data Index: 428147 (C4 (Web Text))
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5004. Min Range: -2.5004
Max Act: 2.1696. Min Act: -0.0001
Data Index: 748800 (C4 (Web Text))
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5004. Min Range: -2.5004
Max Act: 1.9574. Min Act: -0.0002
Data Index: 970933 (C4 (Web Text))
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5004. Min Range: -2.5004
Max Act: 1.6669. Min Act: -0.0001
Data Index: 1174387 (C4 (Web Text))
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #19