Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2149 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 3.1132. Min Range: -3.1132
Max Act: 3.1132. Min Act: -0.0001
Data Index: 390110 (C4 (Web Text))
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1132. Min Range: -3.1132
Max Act: 2.8800. Min Act: -0.0001
Data Index: 1110467 (C4 (Web Text))
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1132. Min Range: -3.1132
Max Act: 2.6063. Min Act: -0.0001
Data Index: 637325 (C4 (Web Text))
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1132. Min Range: -3.1132
Max Act: 2.4190. Min Act: -0.0001
Data Index: 463092 (C4 (Web Text))
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1132. Min Range: -3.1132
Max Act: 2.6156. Min Act: -0.0001
Data Index: 1109018 (C4 (Web Text))
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1132. Min Range: -3.1132
Max Act: 2.3424. Min Act: -0.0001
Data Index: 343214 (C4 (Web Text))
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1132. Min Range: -3.1132
Max Act: 2.5975. Min Act: -0.0001
Data Index: 204836 (C4 (Web Text))
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1132. Min Range: -3.1132
Max Act: 2.3966. Min Act: -0.0001
Data Index: 1026948 (C4 (Web Text))
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1132. Min Range: -3.1132
Max Act: 2.3368. Min Act: -0.0001
Data Index: 830147 (C4 (Web Text))
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1132. Min Range: -3.1132
Max Act: 2.3378. Min Act: -0.0001
Data Index: 875861 (C4 (Web Text))
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1132. Min Range: -3.1132
Max Act: 2.1670. Min Act: -0.0001
Data Index: 582199 (C4 (Web Text))
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1132. Min Range: -3.1132
Max Act: 2.1383. Min Act: -0.0001
Data Index: 104436 (C4 (Web Text))
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1132. Min Range: -3.1132
Max Act: 2.0123. Min Act: -0.0001
Data Index: 52993 (C4 (Web Text))
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1132. Min Range: -3.1132
Max Act: 2.0629. Min Act: -0.0001
Data Index: 349347 (C4 (Web Text))
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1132. Min Range: -3.1132
Max Act: 2.0596. Min Act: -0.0001
Data Index: 1241793 (C4 (Web Text))
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1132. Min Range: -3.1132
Max Act: 2.0431. Min Act: -0.0001
Data Index: 398509 (C4 (Web Text))
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1132. Min Range: -3.1132
Max Act: 1.9235. Min Act: -0.0001
Data Index: 228159 (C4 (Web Text))
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1132. Min Range: -3.1132
Max Act: 1.9219. Min Act: -0.0001
Data Index: 1054516 (C4 (Web Text))
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1132. Min Range: -3.1132
Max Act: 2.1535. Min Act: -0.0001
Data Index: 600842 (C4 (Web Text))
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1132. Min Range: -3.1132
Max Act: 2.0153. Min Act: -0.0001
Data Index: 307663 (C4 (Web Text))
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #19