Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3239 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 2.7875. Min Range: -2.7875
Max Act: 2.7875. Min Act: -0.0001
Data Index: 203662 (C4 (Web Text))
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7875. Min Range: -2.7875
Max Act: 2.4913. Min Act: -0.0001
Data Index: 708554 (C4 (Web Text))
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7875. Min Range: -2.7875
Max Act: 2.3837. Min Act: -0.0001
Data Index: 308222 (C4 (Web Text))
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7875. Min Range: -2.7875
Max Act: 2.1527. Min Act: -0.0001
Data Index: 103113 (C4 (Web Text))
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7875. Min Range: -2.7875
Max Act: 2.1254. Min Act: -0.0001
Data Index: 242184 (C4 (Web Text))
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7875. Min Range: -2.7875
Max Act: 1.8910. Min Act: -0.0001
Data Index: 1379261 (Python Code)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7875. Min Range: -2.7875
Max Act: 2.0930. Min Act: -0.0001
Data Index: 81089 (C4 (Web Text))
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7875. Min Range: -2.7875
Max Act: 1.9488. Min Act: -0.0001
Data Index: 175453 (C4 (Web Text))
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7875. Min Range: -2.7875
Max Act: 2.1490. Min Act: -0.0000
Data Index: 845597 (C4 (Web Text))
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7875. Min Range: -2.7875
Max Act: 1.9281. Min Act: -0.0001
Data Index: 460529 (C4 (Web Text))
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7875. Min Range: -2.7875
Max Act: 1.9064. Min Act: -0.0001
Data Index: 1310345 (C4 (Web Text))
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7875. Min Range: -2.7875
Max Act: 1.8849. Min Act: -0.0000
Data Index: 1586660 (Python Code)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7875. Min Range: -2.7875
Max Act: 1.9724. Min Act: -0.0000
Data Index: 860059 (C4 (Web Text))
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7875. Min Range: -2.7875
Max Act: 1.9270. Min Act: -0.0001
Data Index: 77546 (C4 (Web Text))
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7875. Min Range: -2.7875
Max Act: 2.1530. Min Act: -0.0001
Data Index: 1145190 (C4 (Web Text))
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7875. Min Range: -2.7875
Max Act: 1.8019. Min Act: -0.0001
Data Index: 608529 (C4 (Web Text))
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7875. Min Range: -2.7875
Max Act: 1.8047. Min Act: -0.0001
Data Index: 1613287 (Python Code)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7875. Min Range: -2.7875
Max Act: 1.8811. Min Act: -0.0001
Data Index: 1080041 (C4 (Web Text))
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7875. Min Range: -2.7875
Max Act: 1.8613. Min Act: -0.0001
Data Index: 279704 (C4 (Web Text))
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7875. Min Range: -2.7875
Max Act: 1.7896. Min Act: -0.0001
Data Index: 1493872 (Python Code)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #19