Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 4985 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 3.3103. Min Range: -3.3103
Max Act: 3.3103. Min Act: -0.0001
Data Index: 1295839 (C4 (Web Text))
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3103. Min Range: -3.3103
Max Act: 2.6140. Min Act: -0.0001
Data Index: 455735 (C4 (Web Text))
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3103. Min Range: -3.3103
Max Act: 2.4983. Min Act: -0.0001
Data Index: 377210 (C4 (Web Text))
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3103. Min Range: -3.3103
Max Act: 2.3037. Min Act: -0.0001
Data Index: 1483018 (Python Code)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3103. Min Range: -3.3103
Max Act: 2.4227. Min Act: -0.0001
Data Index: 795765 (C4 (Web Text))
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3103. Min Range: -3.3103
Max Act: 2.3282. Min Act: -0.0001
Data Index: 320459 (C4 (Web Text))
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3103. Min Range: -3.3103
Max Act: 2.2230. Min Act: -0.0001
Data Index: 727671 (C4 (Web Text))
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3103. Min Range: -3.3103
Max Act: 2.0805. Min Act: -0.0001
Data Index: 678107 (C4 (Web Text))
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3103. Min Range: -3.3103
Max Act: 2.0969. Min Act: -0.0001
Data Index: 1295798 (C4 (Web Text))
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3103. Min Range: -3.3103
Max Act: 2.2898. Min Act: -0.0001
Data Index: 24208 (C4 (Web Text))
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3103. Min Range: -3.3103
Max Act: 2.0731. Min Act: -0.0001
Data Index: 1596211 (Python Code)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3103. Min Range: -3.3103
Max Act: 2.1565. Min Act: -0.0001
Data Index: 1349234 (C4 (Web Text))
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3103. Min Range: -3.3103
Max Act: 2.1312. Min Act: -0.0001
Data Index: 2129 (C4 (Web Text))
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3103. Min Range: -3.3103
Max Act: 2.0165. Min Act: -0.0001
Data Index: 980451 (C4 (Web Text))
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3103. Min Range: -3.3103
Max Act: 2.1069. Min Act: -0.0001
Data Index: 69576 (C4 (Web Text))
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3103. Min Range: -3.3103
Max Act: 2.1072. Min Act: -0.0001
Data Index: 1069684 (C4 (Web Text))
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3103. Min Range: -3.3103
Max Act: 2.2044. Min Act: -0.0001
Data Index: 930875 (C4 (Web Text))
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3103. Min Range: -3.3103
Max Act: 1.7825. Min Act: -0.0001
Data Index: 816557 (C4 (Web Text))
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3103. Min Range: -3.3103
Max Act: 2.0735. Min Act: -0.0001
Data Index: 1015475 (C4 (Web Text))
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3103. Min Range: -3.3103
Max Act: 2.0254. Min Act: -0.0001
Data Index: 1050810 (C4 (Web Text))
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #19