Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 99 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 2.1283. Min Range: -2.1283
Max Act: 2.1283. Min Act: -0.0001
Data Index: 915825 (C4 (Web Text))
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.1283. Min Range: -2.1283
Max Act: 1.6550. Min Act: -0.0001
Data Index: 441640 (C4 (Web Text))
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.1283. Min Range: -2.1283
Max Act: 1.6574. Min Act: -0.0001
Data Index: 778869 (C4 (Web Text))
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.1283. Min Range: -2.1283
Max Act: 1.6413. Min Act: -0.0001
Data Index: 558194 (C4 (Web Text))
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.1283. Min Range: -2.1283
Max Act: 1.5314. Min Act: -0.0001
Data Index: 966332 (C4 (Web Text))
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.1283. Min Range: -2.1283
Max Act: 1.3987. Min Act: -0.0001
Data Index: 911672 (C4 (Web Text))
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.1283. Min Range: -2.1283
Max Act: 1.4682. Min Act: -0.0001
Data Index: 544784 (C4 (Web Text))
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.1283. Min Range: -2.1283
Max Act: 1.5974. Min Act: -0.0001
Data Index: 558296 (C4 (Web Text))
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.1283. Min Range: -2.1283
Max Act: 1.3739. Min Act: -0.0001
Data Index: 1644634 (Python Code)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.1283. Min Range: -2.1283
Max Act: 1.5192. Min Act: -0.0001
Data Index: 782624 (C4 (Web Text))
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.1283. Min Range: -2.1283
Max Act: 1.3946. Min Act: -0.0001
Data Index: 936141 (C4 (Web Text))
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.1283. Min Range: -2.1283
Max Act: 1.3540. Min Act: -0.0001
Data Index: 301589 (C4 (Web Text))
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.1283. Min Range: -2.1283
Max Act: 1.3536. Min Act: -0.0001
Data Index: 1649288 (Python Code)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.1283. Min Range: -2.1283
Max Act: 1.3100. Min Act: -0.0001
Data Index: 357580 (C4 (Web Text))
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.1283. Min Range: -2.1283
Max Act: 1.3860. Min Act: -0.0001
Data Index: 798910 (C4 (Web Text))
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.1283. Min Range: -2.1283
Max Act: 1.3404. Min Act: -0.0001
Data Index: 344239 (C4 (Web Text))
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.1283. Min Range: -2.1283
Max Act: 1.3413. Min Act: -0.0001
Data Index: 337134 (C4 (Web Text))
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.1283. Min Range: -2.1283
Max Act: 1.3315. Min Act: -0.0001
Data Index: 784805 (C4 (Web Text))
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.1283. Min Range: -2.1283
Max Act: 1.3224. Min Act: -0.0001
Data Index: 1036433 (C4 (Web Text))
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.1283. Min Range: -2.1283
Max Act: 1.2988. Min Act: -0.0001
Data Index: 203957 (C4 (Web Text))
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #19