Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3201 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 2.0021. Min Range: -2.0021
Max Act: 2.0021. Min Act: -0.0001
Data Index: 1312602 (C4 (Web Text))
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.0021. Min Range: -2.0021
Max Act: 1.7438. Min Act: -0.0001
Data Index: 1154280 (C4 (Web Text))
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.0021. Min Range: -2.0021
Max Act: 1.6011. Min Act: -0.0001
Data Index: 1083431 (C4 (Web Text))
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.0021. Min Range: -2.0021
Max Act: 1.5386. Min Act: -0.0001
Data Index: 1148791 (C4 (Web Text))
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.0021. Min Range: -2.0021
Max Act: 1.3337. Min Act: -0.0001
Data Index: 191850 (C4 (Web Text))
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.0021. Min Range: -2.0021
Max Act: 1.1200. Min Act: -0.0001
Data Index: 202448 (C4 (Web Text))
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.0021. Min Range: -2.0021
Max Act: 1.2247. Min Act: -0.0001
Data Index: 1122672 (C4 (Web Text))
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.0021. Min Range: -2.0021
Max Act: 1.0720. Min Act: -0.0001
Data Index: 1206336 (C4 (Web Text))
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.0021. Min Range: -2.0021
Max Act: 1.0058. Min Act: -0.0001
Data Index: 864724 (C4 (Web Text))
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.0021. Min Range: -2.0021
Max Act: 1.2713. Min Act: -0.0001
Data Index: 189672 (C4 (Web Text))
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.0021. Min Range: -2.0021
Max Act: 1.1804. Min Act: -0.0001
Data Index: 557253 (C4 (Web Text))
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.0021. Min Range: -2.0021
Max Act: 1.0912. Min Act: -0.0001
Data Index: 752654 (C4 (Web Text))
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.0021. Min Range: -2.0021
Max Act: 1.2124. Min Act: -0.0001
Data Index: 1329219 (C4 (Web Text))
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.0021. Min Range: -2.0021
Max Act: 1.1312. Min Act: -0.0001
Data Index: 1089244 (C4 (Web Text))
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.0021. Min Range: -2.0021
Max Act: 0.9873. Min Act: -0.0001
Data Index: 97802 (C4 (Web Text))
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.0021. Min Range: -2.0021
Max Act: 1.2258. Min Act: -0.0001
Data Index: 1230622 (C4 (Web Text))
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.0021. Min Range: -2.0021
Max Act: 1.0569. Min Act: -0.0001
Data Index: 147360 (C4 (Web Text))
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.0021. Min Range: -2.0021
Max Act: 0.9392. Min Act: -0.0001
Data Index: 849898 (C4 (Web Text))
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.0021. Min Range: -2.0021
Max Act: 1.0758. Min Act: -0.0001
Data Index: 103638 (C4 (Web Text))
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.0021. Min Range: -2.0021
Max Act: 1.0171. Min Act: -0.0001
Data Index: 550142 (C4 (Web Text))
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #19