Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3068 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 2.3227. Min Range: -2.3227
Max Act: 2.3227. Min Act: -0.0001
Data Index: 518562 (C4 (Web Text))
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.3227. Min Range: -2.3227
Max Act: 2.1113. Min Act: -0.0001
Data Index: 393876 (C4 (Web Text))
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.3227. Min Range: -2.3227
Max Act: 2.1269. Min Act: -0.0001
Data Index: 1121769 (C4 (Web Text))
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.3227. Min Range: -2.3227
Max Act: 2.0774. Min Act: -0.0001
Data Index: 332674 (C4 (Web Text))
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.3227. Min Range: -2.3227
Max Act: 2.0376. Min Act: -0.0001
Data Index: 1020350 (C4 (Web Text))
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.3227. Min Range: -2.3227
Max Act: 2.0128. Min Act: -0.0001
Data Index: 308728 (C4 (Web Text))
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.3227. Min Range: -2.3227
Max Act: 1.9154. Min Act: -0.0001
Data Index: 763100 (C4 (Web Text))
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.3227. Min Range: -2.3227
Max Act: 1.8832. Min Act: -0.0001
Data Index: 750952 (C4 (Web Text))
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.3227. Min Range: -2.3227
Max Act: 2.0863. Min Act: -0.0001
Data Index: 725198 (C4 (Web Text))
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.3227. Min Range: -2.3227
Max Act: 1.9661. Min Act: -0.0001
Data Index: 697877 (C4 (Web Text))
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.3227. Min Range: -2.3227
Max Act: 1.7761. Min Act: -0.0001
Data Index: 1330442 (C4 (Web Text))
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.3227. Min Range: -2.3227
Max Act: 1.8799. Min Act: -0.0001
Data Index: 1153663 (C4 (Web Text))
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.3227. Min Range: -2.3227
Max Act: 1.7505. Min Act: -0.0001
Data Index: 38920 (C4 (Web Text))
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.3227. Min Range: -2.3227
Max Act: 1.8256. Min Act: -0.0001
Data Index: 882166 (C4 (Web Text))
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.3227. Min Range: -2.3227
Max Act: 1.8284. Min Act: -0.0001
Data Index: 1229579 (C4 (Web Text))
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.3227. Min Range: -2.3227
Max Act: 1.6704. Min Act: -0.0001
Data Index: 285536 (C4 (Web Text))
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.3227. Min Range: -2.3227
Max Act: 1.8482. Min Act: -0.0001
Data Index: 619531 (C4 (Web Text))
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.3227. Min Range: -2.3227
Max Act: 1.7244. Min Act: -0.0001
Data Index: 948744 (C4 (Web Text))
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.3227. Min Range: -2.3227
Max Act: 1.7239. Min Act: -0.0001
Data Index: 603065 (C4 (Web Text))
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.3227. Min Range: -2.3227
Max Act: 1.4220. Min Act: -0.0001
Data Index: 1052371 (C4 (Web Text))
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #19