Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1836 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 5.2489. Min Range: -5.2489
Max Act: 4.7925. Min Act: -0.0001
Data Index: 908625 (C4 (Web Text))
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2489. Min Range: -5.2489
Max Act: 5.2489. Min Act: -0.0001
Data Index: 362252 (C4 (Web Text))
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2489. Min Range: -5.2489
Max Act: 4.8889. Min Act: -0.0001
Data Index: 560498 (C4 (Web Text))
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2489. Min Range: -5.2489
Max Act: 5.0556. Min Act: -0.0001
Data Index: 782442 (C4 (Web Text))
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2489. Min Range: -5.2489
Max Act: 4.6532. Min Act: -0.0001
Data Index: 641429 (C4 (Web Text))
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2489. Min Range: -5.2489
Max Act: 4.3893. Min Act: -0.0001
Data Index: 1088913 (C4 (Web Text))
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2489. Min Range: -5.2489
Max Act: 4.6681. Min Act: -0.0001
Data Index: 796491 (C4 (Web Text))
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2489. Min Range: -5.2489
Max Act: 4.4988. Min Act: -0.0001
Data Index: 644794 (C4 (Web Text))
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2489. Min Range: -5.2489
Max Act: 4.4322. Min Act: -0.0001
Data Index: 66517 (C4 (Web Text))
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2489. Min Range: -5.2489
Max Act: 4.5695. Min Act: -0.0001
Data Index: 1339388 (C4 (Web Text))
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2489. Min Range: -5.2489
Max Act: 4.3371. Min Act: -0.0001
Data Index: 1975 (C4 (Web Text))
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2489. Min Range: -5.2489
Max Act: 4.3287. Min Act: -0.0001
Data Index: 228663 (C4 (Web Text))
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2489. Min Range: -5.2489
Max Act: 4.6523. Min Act: -0.0001
Data Index: 243579 (C4 (Web Text))
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2489. Min Range: -5.2489
Max Act: 4.1820. Min Act: -0.0001
Data Index: 1176181 (C4 (Web Text))
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2489. Min Range: -5.2489
Max Act: 4.2125. Min Act: -0.0001
Data Index: 402834 (C4 (Web Text))
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2489. Min Range: -5.2489
Max Act: 4.3443. Min Act: -0.0001
Data Index: 348182 (C4 (Web Text))
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2489. Min Range: -5.2489
Max Act: 4.4233. Min Act: -0.0001
Data Index: 90436 (C4 (Web Text))
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2489. Min Range: -5.2489
Max Act: 4.0230. Min Act: -0.0001
Data Index: 97439 (C4 (Web Text))
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2489. Min Range: -5.2489
Max Act: 4.1478. Min Act: -0.0001
Data Index: 602853 (C4 (Web Text))
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2489. Min Range: -5.2489
Max Act: 4.1491. Min Act: -0.0001
Data Index: 244175 (C4 (Web Text))
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #19