Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3605 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 2.4111. Min Range: -2.4111
Max Act: 2.4111. Min Act: -0.0001
Data Index: 819821 (C4 (Web Text))
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.4111. Min Range: -2.4111
Max Act: 2.0402. Min Act: -0.0001
Data Index: 894215 (C4 (Web Text))
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.4111. Min Range: -2.4111
Max Act: 2.0986. Min Act: -0.0001
Data Index: 823737 (C4 (Web Text))
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.4111. Min Range: -2.4111
Max Act: 1.9040. Min Act: -0.0001
Data Index: 962786 (C4 (Web Text))
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.4111. Min Range: -2.4111
Max Act: 1.9902. Min Act: -0.0001
Data Index: 553720 (C4 (Web Text))
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.4111. Min Range: -2.4111
Max Act: 1.8725. Min Act: -0.0001
Data Index: 460941 (C4 (Web Text))
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.4111. Min Range: -2.4111
Max Act: 2.0105. Min Act: -0.0001
Data Index: 1100437 (C4 (Web Text))
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.4111. Min Range: -2.4111
Max Act: 1.8132. Min Act: -0.0001
Data Index: 663556 (C4 (Web Text))
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.4111. Min Range: -2.4111
Max Act: 1.9078. Min Act: -0.0001
Data Index: 649193 (C4 (Web Text))
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.4111. Min Range: -2.4111
Max Act: 1.7936. Min Act: -0.0001
Data Index: 957866 (C4 (Web Text))
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.4111. Min Range: -2.4111
Max Act: 1.8703. Min Act: -0.0001
Data Index: 647677 (C4 (Web Text))
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.4111. Min Range: -2.4111
Max Act: 1.8650. Min Act: -0.0001
Data Index: 808814 (C4 (Web Text))
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.4111. Min Range: -2.4111
Max Act: 1.7514. Min Act: -0.0001
Data Index: 211453 (C4 (Web Text))
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.4111. Min Range: -2.4111
Max Act: 1.8259. Min Act: -0.0001
Data Index: 193679 (C4 (Web Text))
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.4111. Min Range: -2.4111
Max Act: 1.7260. Min Act: -0.0001
Data Index: 97459 (C4 (Web Text))
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.4111. Min Range: -2.4111
Max Act: 1.7422. Min Act: -0.0001
Data Index: 173114 (C4 (Web Text))
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.4111. Min Range: -2.4111
Max Act: 1.7187. Min Act: -0.0001
Data Index: 284670 (C4 (Web Text))
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.4111. Min Range: -2.4111
Max Act: 1.6282. Min Act: -0.0001
Data Index: 1086109 (C4 (Web Text))
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.4111. Min Range: -2.4111
Max Act: 1.8517. Min Act: -0.0001
Data Index: 437767 (C4 (Web Text))
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.4111. Min Range: -2.4111
Max Act: 1.7513. Min Act: -0.0001
Data Index: 462237 (C4 (Web Text))
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #19