Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1248 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 1.4325. Min Range: -1.4325
Max Act: 1.4325. Min Act: -0.0001
Data Index: 1187627 (C4 (Web Text))
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.4325. Min Range: -1.4325
Max Act: 1.3887. Min Act: -0.0001
Data Index: 1133356 (C4 (Web Text))
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.4325. Min Range: -1.4325
Max Act: 1.4077. Min Act: -0.0001
Data Index: 480373 (C4 (Web Text))
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.4325. Min Range: -1.4325
Max Act: 1.3918. Min Act: -0.0001
Data Index: 924756 (C4 (Web Text))
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.4325. Min Range: -1.4325
Max Act: 1.3451. Min Act: -0.0001
Data Index: 154364 (C4 (Web Text))
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.4325. Min Range: -1.4325
Max Act: 1.3479. Min Act: -0.0001
Data Index: 233052 (C4 (Web Text))
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.4325. Min Range: -1.4325
Max Act: 1.2785. Min Act: -0.0001
Data Index: 371058 (C4 (Web Text))
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.4325. Min Range: -1.4325
Max Act: 1.3527. Min Act: -0.0001
Data Index: 2989 (C4 (Web Text))
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.4325. Min Range: -1.4325
Max Act: 1.2380. Min Act: -0.0001
Data Index: 953023 (C4 (Web Text))
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.4325. Min Range: -1.4325
Max Act: 1.2648. Min Act: -0.0001
Data Index: 98616 (C4 (Web Text))
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.4325. Min Range: -1.4325
Max Act: 1.2355. Min Act: -0.0001
Data Index: 111613 (C4 (Web Text))
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.4325. Min Range: -1.4325
Max Act: 1.2936. Min Act: -0.0001
Data Index: 1406240 (Python Code)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.4325. Min Range: -1.4325
Max Act: 1.2955. Min Act: -0.0001
Data Index: 291792 (C4 (Web Text))
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.4325. Min Range: -1.4325
Max Act: 1.2945. Min Act: -0.0001
Data Index: 1209364 (C4 (Web Text))
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.4325. Min Range: -1.4325
Max Act: 1.2421. Min Act: -0.0001
Data Index: 960358 (C4 (Web Text))
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.4325. Min Range: -1.4325
Max Act: 1.3006. Min Act: -0.0001
Data Index: 1150462 (C4 (Web Text))
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.4325. Min Range: -1.4325
Max Act: 1.2655. Min Act: -0.0001
Data Index: 1143776 (C4 (Web Text))
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.4325. Min Range: -1.4325
Max Act: 1.1848. Min Act: -0.0001
Data Index: 734352 (C4 (Web Text))
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.4325. Min Range: -1.4325
Max Act: 1.2953. Min Act: -0.0001
Data Index: 690937 (C4 (Web Text))
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.4325. Min Range: -1.4325
Max Act: 1.2102. Min Act: -0.0001
Data Index: 1596836 (Python Code)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #19