Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1678 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 2.1237. Min Range: -2.1237
Max Act: 2.0040. Min Act: -0.0001
Data Index: 957214 (C4 (Web Text))
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.1237. Min Range: -2.1237
Max Act: 2.0709. Min Act: -0.0001
Data Index: 1169882 (C4 (Web Text))
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.1237. Min Range: -2.1237
Max Act: 2.0546. Min Act: -0.0001
Data Index: 1035755 (C4 (Web Text))
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.1237. Min Range: -2.1237
Max Act: 2.1237. Min Act: -0.0001
Data Index: 1176075 (C4 (Web Text))
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.1237. Min Range: -2.1237
Max Act: 1.9857. Min Act: -0.0001
Data Index: 122710 (C4 (Web Text))
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.1237. Min Range: -2.1237
Max Act: 1.9194. Min Act: -0.0001
Data Index: 146350 (C4 (Web Text))
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.1237. Min Range: -2.1237
Max Act: 1.9386. Min Act: -0.0001
Data Index: 1158225 (C4 (Web Text))
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.1237. Min Range: -2.1237
Max Act: 1.9635. Min Act: -0.0001
Data Index: 118252 (C4 (Web Text))
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.1237. Min Range: -2.1237
Max Act: 1.9876. Min Act: -0.0001
Data Index: 1232745 (C4 (Web Text))
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.1237. Min Range: -2.1237
Max Act: 1.8446. Min Act: -0.0001
Data Index: 425966 (C4 (Web Text))
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.1237. Min Range: -2.1237
Max Act: 1.7796. Min Act: -0.0001
Data Index: 1249040 (C4 (Web Text))
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.1237. Min Range: -2.1237
Max Act: 1.8673. Min Act: -0.0001
Data Index: 365818 (C4 (Web Text))
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.1237. Min Range: -2.1237
Max Act: 1.8437. Min Act: -0.0001
Data Index: 386268 (C4 (Web Text))
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.1237. Min Range: -2.1237
Max Act: 1.8005. Min Act: -0.0001
Data Index: 963188 (C4 (Web Text))
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.1237. Min Range: -2.1237
Max Act: 1.8823. Min Act: -0.0001
Data Index: 954611 (C4 (Web Text))
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.1237. Min Range: -2.1237
Max Act: 1.7737. Min Act: -0.0001
Data Index: 432586 (C4 (Web Text))
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.1237. Min Range: -2.1237
Max Act: 1.7636. Min Act: -0.0001
Data Index: 666546 (C4 (Web Text))
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.1237. Min Range: -2.1237
Max Act: 1.7716. Min Act: -0.0001
Data Index: 675568 (C4 (Web Text))
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.1237. Min Range: -2.1237
Max Act: 1.7509. Min Act: -0.0001
Data Index: 235486 (C4 (Web Text))
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.1237. Min Range: -2.1237
Max Act: 1.6824. Min Act: -0.0001
Data Index: 136935 (C4 (Web Text))
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #19