Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 4034 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 2.0201. Min Range: -2.0201
Max Act: 2.0201. Min Act: -0.0001
Data Index: 748185 (C4 (Web Text))
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.0201. Min Range: -2.0201
Max Act: 1.7588. Min Act: -0.0001
Data Index: 887689 (C4 (Web Text))
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.0201. Min Range: -2.0201
Max Act: 1.8182. Min Act: -0.0001
Data Index: 1058965 (C4 (Web Text))
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.0201. Min Range: -2.0201
Max Act: 1.5991. Min Act: -0.0001
Data Index: 531843 (C4 (Web Text))
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.0201. Min Range: -2.0201
Max Act: 1.5677. Min Act: -0.0001
Data Index: 341764 (C4 (Web Text))
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.0201. Min Range: -2.0201
Max Act: 1.5988. Min Act: -0.0001
Data Index: 42752 (C4 (Web Text))
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.0201. Min Range: -2.0201
Max Act: 1.5996. Min Act: -0.0001
Data Index: 854249 (C4 (Web Text))
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.0201. Min Range: -2.0201
Max Act: 1.5498. Min Act: -0.0001
Data Index: 369598 (C4 (Web Text))
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.0201. Min Range: -2.0201
Max Act: 1.5544. Min Act: -0.0001
Data Index: 314544 (C4 (Web Text))
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.0201. Min Range: -2.0201
Max Act: 1.5448. Min Act: -0.0001
Data Index: 341093 (C4 (Web Text))
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.0201. Min Range: -2.0201
Max Act: 1.4000. Min Act: -0.0001
Data Index: 908703 (C4 (Web Text))
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.0201. Min Range: -2.0201
Max Act: 1.5477. Min Act: -0.0001
Data Index: 1226759 (C4 (Web Text))
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.0201. Min Range: -2.0201
Max Act: 1.4981. Min Act: -0.0001
Data Index: 401691 (C4 (Web Text))
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.0201. Min Range: -2.0201
Max Act: 1.4864. Min Act: -0.0001
Data Index: 1177899 (C4 (Web Text))
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.0201. Min Range: -2.0201
Max Act: 1.4845. Min Act: -0.0001
Data Index: 930916 (C4 (Web Text))
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.0201. Min Range: -2.0201
Max Act: 1.4771. Min Act: -0.0001
Data Index: 128326 (C4 (Web Text))
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.0201. Min Range: -2.0201
Max Act: 1.5161. Min Act: -0.0001
Data Index: 1168452 (C4 (Web Text))
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.0201. Min Range: -2.0201
Max Act: 1.5561. Min Act: -0.0001
Data Index: 1344990 (C4 (Web Text))
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.0201. Min Range: -2.0201
Max Act: 1.4936. Min Act: -0.0001
Data Index: 975443 (C4 (Web Text))
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.0201. Min Range: -2.0201
Max Act: 1.4560. Min Act: -0.0001
Data Index: 527138 (C4 (Web Text))
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #19