Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 919 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 4.7173. Min Range: -4.7173
Max Act: 4.7173. Min Act: -0.0001
Data Index: 73027 (C4 (Web Text))
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7173. Min Range: -4.7173
Max Act: 2.8720. Min Act: -0.0001
Data Index: 494370 (C4 (Web Text))
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7173. Min Range: -4.7173
Max Act: 2.3217. Min Act: -0.0002
Data Index: 1142864 (C4 (Web Text))
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7173. Min Range: -4.7173
Max Act: 2.2880. Min Act: -0.0001
Data Index: 1270544 (C4 (Web Text))
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7173. Min Range: -4.7173
Max Act: 2.2040. Min Act: -0.0001
Data Index: 1269388 (C4 (Web Text))
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7173. Min Range: -4.7173
Max Act: 2.2507. Min Act: -0.0001
Data Index: 1147030 (C4 (Web Text))
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7173. Min Range: -4.7173
Max Act: 2.2384. Min Act: -0.0001
Data Index: 827475 (C4 (Web Text))
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7173. Min Range: -4.7173
Max Act: 2.1527. Min Act: -0.0001
Data Index: 450507 (C4 (Web Text))
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7173. Min Range: -4.7173
Max Act: 2.1746. Min Act: -0.0001
Data Index: 797688 (C4 (Web Text))
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7173. Min Range: -4.7173
Max Act: 2.0903. Min Act: -0.0001
Data Index: 78641 (C4 (Web Text))
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7173. Min Range: -4.7173
Max Act: 2.1462. Min Act: -0.0001
Data Index: 785120 (C4 (Web Text))
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7173. Min Range: -4.7173
Max Act: 2.1045. Min Act: -0.0001
Data Index: 1356071 (C4 (Web Text))
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7173. Min Range: -4.7173
Max Act: 2.0495. Min Act: -0.0001
Data Index: 243236 (C4 (Web Text))
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7173. Min Range: -4.7173
Max Act: 1.9316. Min Act: -0.0001
Data Index: 770219 (C4 (Web Text))
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7173. Min Range: -4.7173
Max Act: 2.0201. Min Act: -0.0001
Data Index: 15494 (C4 (Web Text))
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7173. Min Range: -4.7173
Max Act: 1.8967. Min Act: -0.0001
Data Index: 1032213 (C4 (Web Text))
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7173. Min Range: -4.7173
Max Act: 2.0578. Min Act: -0.0001
Data Index: 434084 (C4 (Web Text))
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7173. Min Range: -4.7173
Max Act: 1.8957. Min Act: -0.0001
Data Index: 1210124 (C4 (Web Text))
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7173. Min Range: -4.7173
Max Act: 1.8172. Min Act: -0.0001
Data Index: 1226151 (C4 (Web Text))
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7173. Min Range: -4.7173
Max Act: 1.7897. Min Act: -0.0001
Data Index: 1237517 (C4 (Web Text))
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #19