Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2996 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 2.2057. Min Range: -2.2057
Max Act: 2.2057. Min Act: -0.0001
Data Index: 411205 (C4 (Web Text))
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.2057. Min Range: -2.2057
Max Act: 2.1488. Min Act: -0.0001
Data Index: 454948 (C4 (Web Text))
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.2057. Min Range: -2.2057
Max Act: 1.7700. Min Act: -0.0001
Data Index: 916910 (C4 (Web Text))
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.2057. Min Range: -2.2057
Max Act: 2.1358. Min Act: -0.0001
Data Index: 500076 (C4 (Web Text))
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.2057. Min Range: -2.2057
Max Act: 1.6706. Min Act: -0.0001
Data Index: 470759 (C4 (Web Text))
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.2057. Min Range: -2.2057
Max Act: 1.7470. Min Act: -0.0001
Data Index: 1126457 (C4 (Web Text))
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.2057. Min Range: -2.2057
Max Act: 1.6940. Min Act: -0.0001
Data Index: 903625 (C4 (Web Text))
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.2057. Min Range: -2.2057
Max Act: 1.6669. Min Act: -0.0001
Data Index: 217723 (C4 (Web Text))
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.2057. Min Range: -2.2057
Max Act: 1.8911. Min Act: -0.0001
Data Index: 1012564 (C4 (Web Text))
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.2057. Min Range: -2.2057
Max Act: 1.7213. Min Act: -0.0001
Data Index: 1028237 (C4 (Web Text))
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.2057. Min Range: -2.2057
Max Act: 1.7240. Min Act: -0.0001
Data Index: 324750 (C4 (Web Text))
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.2057. Min Range: -2.2057
Max Act: 1.6445. Min Act: -0.0001
Data Index: 1084410 (C4 (Web Text))
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.2057. Min Range: -2.2057
Max Act: 1.5163. Min Act: -0.0001
Data Index: 1241478 (C4 (Web Text))
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.2057. Min Range: -2.2057
Max Act: 1.7119. Min Act: -0.0001
Data Index: 220604 (C4 (Web Text))
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.2057. Min Range: -2.2057
Max Act: 1.5981. Min Act: -0.0001
Data Index: 960711 (C4 (Web Text))
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.2057. Min Range: -2.2057
Max Act: 1.4312. Min Act: -0.0001
Data Index: 923537 (C4 (Web Text))
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.2057. Min Range: -2.2057
Max Act: 1.5163. Min Act: -0.0001
Data Index: 1210224 (C4 (Web Text))
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.2057. Min Range: -2.2057
Max Act: 1.4766. Min Act: -0.0000
Data Index: 1451673 (Python Code)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.2057. Min Range: -2.2057
Max Act: 1.4668. Min Act: -0.0001
Data Index: 41809 (C4 (Web Text))
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.2057. Min Range: -2.2057
Max Act: 1.4002. Min Act: -0.0000
Data Index: 5668 (C4 (Web Text))
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #19