Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1646 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 2.3582. Min Range: -2.3582
Max Act: 2.3582. Min Act: -0.0002
Data Index: 342375 (C4 (Web Text))
Max Activating Token Index: 515
Click toggle to see full textTruncated
Full Text #0
Text #1
Max Range: 2.3582. Min Range: -2.3582
Max Act: 2.2373. Min Act: -0.0002
Data Index: 764782 (C4 (Web Text))
Max Activating Token Index: 502
Click toggle to see full textTruncated
Full Text #1
Text #2
Max Range: 2.3582. Min Range: -2.3582
Max Act: 2.0263. Min Act: -0.0002
Data Index: 1239636 (C4 (Web Text))
Max Activating Token Index: 366
Click toggle to see full textTruncated
Full Text #2
Text #3
Max Range: 2.3582. Min Range: -2.3582
Max Act: 2.0651. Min Act: -0.0002
Data Index: 1089351 (C4 (Web Text))
Max Activating Token Index: 781
Click toggle to see full textTruncated
Full Text #3
Text #4
Max Range: 2.3582. Min Range: -2.3582
Max Act: 1.9977. Min Act: -0.0002
Data Index: 569587 (C4 (Web Text))
Max Activating Token Index: 39
Click toggle to see full textTruncated
Full Text #4
Text #5
Max Range: 2.3582. Min Range: -2.3582
Max Act: 1.7947. Min Act: -0.0002
Data Index: 511830 (C4 (Web Text))
Max Activating Token Index: 30
Click toggle to see full textTruncated
Full Text #5
Text #6
Max Range: 2.3582. Min Range: -2.3582
Max Act: 1.6919. Min Act: -0.0002
Data Index: 1317277 (C4 (Web Text))
Max Activating Token Index: 253
Click toggle to see full textTruncated
Full Text #6
Text #7
Max Range: 2.3582. Min Range: -2.3582
Max Act: 1.5867. Min Act: -0.0002
Data Index: 1046064 (C4 (Web Text))
Max Activating Token Index: 951
Click toggle to see full textTruncated
Full Text #7
Text #8
Max Range: 2.3582. Min Range: -2.3582
Max Act: 1.5832. Min Act: -0.0002
Data Index: 1166988 (C4 (Web Text))
Max Activating Token Index: 157
Click toggle to see full textTruncated
Full Text #8
Text #9
Max Range: 2.3582. Min Range: -2.3582
Max Act: 1.5221. Min Act: -0.0002
Data Index: 1312439 (C4 (Web Text))
Max Activating Token Index: 516
Click toggle to see full textTruncated
Full Text #9
Text #10
Max Range: 2.3582. Min Range: -2.3582
Max Act: 1.5155. Min Act: -0.0002
Data Index: 32114 (C4 (Web Text))
Max Activating Token Index: 286
Click toggle to see full textTruncated
Full Text #10
Text #11
Max Range: 2.3582. Min Range: -2.3582
Max Act: 1.4470. Min Act: -0.0002
Data Index: 309468 (C4 (Web Text))
Max Activating Token Index: 826
Click toggle to see full textTruncated
Full Text #11
Text #12
Max Range: 2.3582. Min Range: -2.3582
Max Act: 1.4774. Min Act: -0.0002
Data Index: 929033 (C4 (Web Text))
Max Activating Token Index: 428
Click toggle to see full textTruncated
Full Text #12
Text #13
Max Range: 2.3582. Min Range: -2.3582
Max Act: 1.4816. Min Act: -0.0002
Data Index: 440268 (C4 (Web Text))
Max Activating Token Index: 959
Click toggle to see full textTruncated
Full Text #13
Text #14
Max Range: 2.3582. Min Range: -2.3582
Max Act: 1.5100. Min Act: -0.0002
Data Index: 1251081 (C4 (Web Text))
Max Activating Token Index: 161
Click toggle to see full textTruncated
Full Text #14
Text #15
Max Range: 2.3582. Min Range: -2.3582
Max Act: 1.4191. Min Act: -0.0002
Data Index: 433673 (C4 (Web Text))
Max Activating Token Index: 787
Click toggle to see full textTruncated
Full Text #15
Text #16
Max Range: 2.3582. Min Range: -2.3582
Max Act: 1.2946. Min Act: -0.0002
Data Index: 1324375 (C4 (Web Text))
Max Activating Token Index: 350
Click toggle to see full textTruncated
Full Text #16
Text #17
Max Range: 2.3582. Min Range: -2.3582
Max Act: 1.3728. Min Act: -0.0002
Data Index: 567394 (C4 (Web Text))
Max Activating Token Index: 932
Click toggle to see full textTruncated
Full Text #17
Text #18
Max Range: 2.3582. Min Range: -2.3582
Max Act: 1.2798. Min Act: -0.0002
Data Index: 647233 (C4 (Web Text))
Max Activating Token Index: 190
Click toggle to see full textTruncated
Full Text #18
Text #19
Max Range: 2.3582. Min Range: -2.3582
Max Act: 1.2734. Min Act: -0.0002
Data Index: 703002 (C4 (Web Text))
Max Activating Token Index: 523
Click toggle to see full textTruncated
Full Text #19