Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3794 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 3.8108. Min Range: -3.8108
Max Act: 3.8108. Min Act: -0.0001
Data Index: 652022 (C4 (Web Text))
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8108. Min Range: -3.8108
Max Act: 2.7650. Min Act: -0.0001
Data Index: 611053 (C4 (Web Text))
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8108. Min Range: -3.8108
Max Act: 2.8194. Min Act: -0.0001
Data Index: 1269721 (C4 (Web Text))
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8108. Min Range: -3.8108
Max Act: 2.9266. Min Act: -0.0001
Data Index: 119845 (C4 (Web Text))
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8108. Min Range: -3.8108
Max Act: 2.6134. Min Act: -0.0001
Data Index: 280030 (C4 (Web Text))
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8108. Min Range: -3.8108
Max Act: 2.7046. Min Act: -0.0001
Data Index: 227530 (C4 (Web Text))
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8108. Min Range: -3.8108
Max Act: 2.4367. Min Act: -0.0001
Data Index: 756056 (C4 (Web Text))
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8108. Min Range: -3.8108
Max Act: 2.6517. Min Act: -0.0001
Data Index: 314212 (C4 (Web Text))
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8108. Min Range: -3.8108
Max Act: 2.2760. Min Act: -0.0000
Data Index: 816666 (C4 (Web Text))
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8108. Min Range: -3.8108
Max Act: 2.3249. Min Act: -0.0001
Data Index: 385370 (C4 (Web Text))
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8108. Min Range: -3.8108
Max Act: 2.5303. Min Act: -0.0001
Data Index: 1003174 (C4 (Web Text))
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8108. Min Range: -3.8108
Max Act: 2.5196. Min Act: -0.0001
Data Index: 507040 (C4 (Web Text))
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8108. Min Range: -3.8108
Max Act: 2.4146. Min Act: -0.0001
Data Index: 79865 (C4 (Web Text))
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8108. Min Range: -3.8108
Max Act: 2.4360. Min Act: -0.0001
Data Index: 176195 (C4 (Web Text))
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8108. Min Range: -3.8108
Max Act: 2.4342. Min Act: -0.0001
Data Index: 1142771 (C4 (Web Text))
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8108. Min Range: -3.8108
Max Act: 2.1962. Min Act: -0.0001
Data Index: 623604 (C4 (Web Text))
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8108. Min Range: -3.8108
Max Act: 2.2771. Min Act: -0.0001
Data Index: 943209 (C4 (Web Text))
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8108. Min Range: -3.8108
Max Act: 2.5765. Min Act: -0.0001
Data Index: 1091019 (C4 (Web Text))
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8108. Min Range: -3.8108
Max Act: 2.3319. Min Act: -0.0001
Data Index: 425281 (C4 (Web Text))
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8108. Min Range: -3.8108
Max Act: 2.3953. Min Act: -0.0001
Data Index: 258649 (C4 (Web Text))
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #19