Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 4422 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 4.4794. Min Range: -4.4794
Max Act: 4.1710. Min Act: -0.0001
Data Index: 363184 (C4 (Web Text))
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4794. Min Range: -4.4794
Max Act: 4.4794. Min Act: -0.0001
Data Index: 513747 (C4 (Web Text))
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4794. Min Range: -4.4794
Max Act: 4.0636. Min Act: -0.0001
Data Index: 655300 (C4 (Web Text))
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4794. Min Range: -4.4794
Max Act: 3.9427. Min Act: -0.0001
Data Index: 390683 (C4 (Web Text))
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4794. Min Range: -4.4794
Max Act: 3.5098. Min Act: -0.0001
Data Index: 279512 (C4 (Web Text))
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4794. Min Range: -4.4794
Max Act: 3.6234. Min Act: -0.0001
Data Index: 605304 (C4 (Web Text))
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4794. Min Range: -4.4794
Max Act: 3.7516. Min Act: -0.0001
Data Index: 1356217 (C4 (Web Text))
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4794. Min Range: -4.4794
Max Act: 3.4415. Min Act: -0.0001
Data Index: 1030066 (C4 (Web Text))
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4794. Min Range: -4.4794
Max Act: 3.2211. Min Act: -0.0001
Data Index: 758288 (C4 (Web Text))
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4794. Min Range: -4.4794
Max Act: 3.5209. Min Act: -0.0001
Data Index: 409988 (C4 (Web Text))
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4794. Min Range: -4.4794
Max Act: 3.2772. Min Act: -0.0001
Data Index: 442339 (C4 (Web Text))
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4794. Min Range: -4.4794
Max Act: 3.2690. Min Act: -0.0001
Data Index: 146551 (C4 (Web Text))
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4794. Min Range: -4.4794
Max Act: 3.0643. Min Act: -0.0001
Data Index: 1252881 (C4 (Web Text))
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4794. Min Range: -4.4794
Max Act: 3.1325. Min Act: -0.0000
Data Index: 19638 (C4 (Web Text))
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4794. Min Range: -4.4794
Max Act: 2.9755. Min Act: -0.0001
Data Index: 176109 (C4 (Web Text))
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4794. Min Range: -4.4794
Max Act: 3.4214. Min Act: -0.0001
Data Index: 558776 (C4 (Web Text))
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4794. Min Range: -4.4794
Max Act: 3.2940. Min Act: -0.0001
Data Index: 297028 (C4 (Web Text))
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4794. Min Range: -4.4794
Max Act: 3.1107. Min Act: -0.0001
Data Index: 67065 (C4 (Web Text))
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4794. Min Range: -4.4794
Max Act: 3.1188. Min Act: -0.0001
Data Index: 1237620 (C4 (Web Text))
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4794. Min Range: -4.4794
Max Act: 3.2413. Min Act: -0.0001
Data Index: 898257 (C4 (Web Text))
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #19