Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 4004 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 0.9610. Min Range: -0.9610
Max Act: 0.9610. Min Act: -0.0001
Data Index: 429912 (C4 (Web Text))
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.9610. Min Range: -0.9610
Max Act: 0.8672. Min Act: -0.0002
Data Index: 603011 (C4 (Web Text))
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.9610. Min Range: -0.9610
Max Act: 0.8612. Min Act: -0.0001
Data Index: 1070381 (C4 (Web Text))
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.9610. Min Range: -0.9610
Max Act: 0.8732. Min Act: -0.0001
Data Index: 1067464 (C4 (Web Text))
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.9610. Min Range: -0.9610
Max Act: 0.9576. Min Act: -0.0001
Data Index: 597678 (C4 (Web Text))
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.9610. Min Range: -0.9610
Max Act: 0.8947. Min Act: -0.0001
Data Index: 248320 (C4 (Web Text))
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.9610. Min Range: -0.9610
Max Act: 0.8643. Min Act: -0.0001
Data Index: 1019193 (C4 (Web Text))
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.9610. Min Range: -0.9610
Max Act: 0.9112. Min Act: -0.0001
Data Index: 734237 (C4 (Web Text))
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.9610. Min Range: -0.9610
Max Act: 0.9356. Min Act: -0.0001
Data Index: 664001 (C4 (Web Text))
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.9610. Min Range: -0.9610
Max Act: 0.8689. Min Act: -0.0001
Data Index: 1015341 (C4 (Web Text))
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.9610. Min Range: -0.9610
Max Act: 0.8157. Min Act: -0.0001
Data Index: 1009842 (C4 (Web Text))
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.9610. Min Range: -0.9610
Max Act: 0.9288. Min Act: -0.0001
Data Index: 724309 (C4 (Web Text))
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.9610. Min Range: -0.9610
Max Act: 0.8639. Min Act: -0.0001
Data Index: 397089 (C4 (Web Text))
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.9610. Min Range: -0.9610
Max Act: 0.8866. Min Act: -0.0001
Data Index: 958478 (C4 (Web Text))
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.9610. Min Range: -0.9610
Max Act: 0.8613. Min Act: -0.0001
Data Index: 376174 (C4 (Web Text))
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.9610. Min Range: -0.9610
Max Act: 0.7381. Min Act: -0.0001
Data Index: 169020 (C4 (Web Text))
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.9610. Min Range: -0.9610
Max Act: 0.8539. Min Act: -0.0001
Data Index: 1066755 (C4 (Web Text))
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.9610. Min Range: -0.9610
Max Act: 0.7925. Min Act: -0.0001
Data Index: 234866 (C4 (Web Text))
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.9610. Min Range: -0.9610
Max Act: 0.8683. Min Act: -0.0001
Data Index: 846700 (C4 (Web Text))
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.9610. Min Range: -0.9610
Max Act: 0.8756. Min Act: -0.0001
Data Index: 821527 (C4 (Web Text))
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #19