Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2229 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 3.1795. Min Range: -3.1795
Max Act: 3.1795. Min Act: -0.0001
Data Index: 1168356 (C4 (Web Text))
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1795. Min Range: -3.1795
Max Act: 2.8179. Min Act: -0.0001
Data Index: 1567607 (Python Code)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1795. Min Range: -3.1795
Max Act: 2.7226. Min Act: -0.0001
Data Index: 164562 (C4 (Web Text))
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1795. Min Range: -3.1795
Max Act: 2.4694. Min Act: -0.0001
Data Index: 1124784 (C4 (Web Text))
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1795. Min Range: -3.1795
Max Act: 2.7739. Min Act: -0.0001
Data Index: 125564 (C4 (Web Text))
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1795. Min Range: -3.1795
Max Act: 2.5783. Min Act: -0.0001
Data Index: 1136886 (C4 (Web Text))
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1795. Min Range: -3.1795
Max Act: 2.4076. Min Act: -0.0001
Data Index: 2137 (C4 (Web Text))
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1795. Min Range: -3.1795
Max Act: 2.4032. Min Act: -0.0001
Data Index: 502200 (C4 (Web Text))
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1795. Min Range: -3.1795
Max Act: 2.3441. Min Act: -0.0001
Data Index: 419577 (C4 (Web Text))
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1795. Min Range: -3.1795
Max Act: 2.2743. Min Act: -0.0001
Data Index: 558279 (C4 (Web Text))
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1795. Min Range: -3.1795
Max Act: 1.9606. Min Act: -0.0001
Data Index: 1024142 (C4 (Web Text))
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1795. Min Range: -3.1795
Max Act: 2.1261. Min Act: -0.0001
Data Index: 594004 (C4 (Web Text))
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1795. Min Range: -3.1795
Max Act: 2.2505. Min Act: -0.0001
Data Index: 218664 (C4 (Web Text))
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1795. Min Range: -3.1795
Max Act: 2.2393. Min Act: -0.0001
Data Index: 1215069 (C4 (Web Text))
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1795. Min Range: -3.1795
Max Act: 2.3722. Min Act: -0.0001
Data Index: 78808 (C4 (Web Text))
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1795. Min Range: -3.1795
Max Act: 2.2500. Min Act: -0.0001
Data Index: 1512481 (Python Code)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1795. Min Range: -3.1795
Max Act: 2.2395. Min Act: -0.0001
Data Index: 1242511 (C4 (Web Text))
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1795. Min Range: -3.1795
Max Act: 2.0046. Min Act: -0.0001
Data Index: 1267064 (C4 (Web Text))
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1795. Min Range: -3.1795
Max Act: 2.2263. Min Act: -0.0001
Data Index: 606269 (C4 (Web Text))
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1795. Min Range: -3.1795
Max Act: 2.3075. Min Act: -0.0001
Data Index: 512601 (C4 (Web Text))
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #19