Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2150 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 2.2168. Min Range: -2.2168
Max Act: 2.2168. Min Act: -0.0000
Data Index: 1180603 (C4 (Web Text))
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.2168. Min Range: -2.2168
Max Act: 2.0699. Min Act: -0.0001
Data Index: 157591 (C4 (Web Text))
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.2168. Min Range: -2.2168
Max Act: 2.0528. Min Act: -0.0001
Data Index: 650377 (C4 (Web Text))
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.2168. Min Range: -2.2168
Max Act: 2.0183. Min Act: -0.0000
Data Index: 2436 (C4 (Web Text))
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.2168. Min Range: -2.2168
Max Act: 1.9432. Min Act: -0.0001
Data Index: 1260449 (C4 (Web Text))
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.2168. Min Range: -2.2168
Max Act: 1.7917. Min Act: -0.0001
Data Index: 9556 (C4 (Web Text))
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.2168. Min Range: -2.2168
Max Act: 1.8285. Min Act: -0.0001
Data Index: 1132762 (C4 (Web Text))
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.2168. Min Range: -2.2168
Max Act: 1.8424. Min Act: -0.0001
Data Index: 171069 (C4 (Web Text))
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.2168. Min Range: -2.2168
Max Act: 1.8047. Min Act: -0.0000
Data Index: 921261 (C4 (Web Text))
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.2168. Min Range: -2.2168
Max Act: 1.6949. Min Act: -0.0000
Data Index: 1161631 (C4 (Web Text))
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.2168. Min Range: -2.2168
Max Act: 1.7702. Min Act: -0.0000
Data Index: 311360 (C4 (Web Text))
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.2168. Min Range: -2.2168
Max Act: 1.8045. Min Act: -0.0001
Data Index: 558876 (C4 (Web Text))
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.2168. Min Range: -2.2168
Max Act: 1.7541. Min Act: -0.0000
Data Index: 208139 (C4 (Web Text))
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.2168. Min Range: -2.2168
Max Act: 1.7543. Min Act: -0.0000
Data Index: 358546 (C4 (Web Text))
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.2168. Min Range: -2.2168
Max Act: 1.6279. Min Act: -0.0001
Data Index: 1058070 (C4 (Web Text))
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.2168. Min Range: -2.2168
Max Act: 1.6070. Min Act: -0.0001
Data Index: 1601218 (Python Code)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.2168. Min Range: -2.2168
Max Act: 1.6028. Min Act: -0.0001
Data Index: 1238029 (C4 (Web Text))
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.2168. Min Range: -2.2168
Max Act: 1.6379. Min Act: -0.0001
Data Index: 255934 (C4 (Web Text))
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.2168. Min Range: -2.2168
Max Act: 1.6278. Min Act: -0.0000
Data Index: 297595 (C4 (Web Text))
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.2168. Min Range: -2.2168
Max Act: 1.6769. Min Act: -0.0000
Data Index: 745732 (C4 (Web Text))
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #19