Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3546 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 2.8922. Min Range: -2.8922
Max Act: 2.8922. Min Act: -0.0000
Data Index: 524538 (C4 (Web Text))
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8922. Min Range: -2.8922
Max Act: 2.7629. Min Act: -0.0001
Data Index: 1145229 (C4 (Web Text))
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8922. Min Range: -2.8922
Max Act: 2.4293. Min Act: -0.0001
Data Index: 444024 (C4 (Web Text))
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8922. Min Range: -2.8922
Max Act: 2.1377. Min Act: -0.0000
Data Index: 1348436 (C4 (Web Text))
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8922. Min Range: -2.8922
Max Act: 2.2168. Min Act: -0.0001
Data Index: 670587 (C4 (Web Text))
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8922. Min Range: -2.8922
Max Act: 1.9212. Min Act: -0.0001
Data Index: 411964 (C4 (Web Text))
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8922. Min Range: -2.8922
Max Act: 2.1033. Min Act: -0.0000
Data Index: 8378 (C4 (Web Text))
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8922. Min Range: -2.8922
Max Act: 1.8148. Min Act: -0.0001
Data Index: 81696 (C4 (Web Text))
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8922. Min Range: -2.8922
Max Act: 2.0239. Min Act: -0.0000
Data Index: 72764 (C4 (Web Text))
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8922. Min Range: -2.8922
Max Act: 1.8688. Min Act: -0.0001
Data Index: 769385 (C4 (Web Text))
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8922. Min Range: -2.8922
Max Act: 1.9453. Min Act: -0.0001
Data Index: 654346 (C4 (Web Text))
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8922. Min Range: -2.8922
Max Act: 1.9383. Min Act: -0.0001
Data Index: 1347691 (C4 (Web Text))
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8922. Min Range: -2.8922
Max Act: 2.0515. Min Act: -0.0001
Data Index: 1352269 (C4 (Web Text))
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8922. Min Range: -2.8922
Max Act: 1.9562. Min Act: -0.0001
Data Index: 719938 (C4 (Web Text))
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8922. Min Range: -2.8922
Max Act: 1.7846. Min Act: -0.0001
Data Index: 1340981 (C4 (Web Text))
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8922. Min Range: -2.8922
Max Act: 1.9644. Min Act: -0.0000
Data Index: 629434 (C4 (Web Text))
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8922. Min Range: -2.8922
Max Act: 1.8673. Min Act: -0.0001
Data Index: 122544 (C4 (Web Text))
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8922. Min Range: -2.8922
Max Act: 1.8584. Min Act: -0.0000
Data Index: 516219 (C4 (Web Text))
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8922. Min Range: -2.8922
Max Act: 1.9568. Min Act: -0.0001
Data Index: 553279 (C4 (Web Text))
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8922. Min Range: -2.8922
Max Act: 2.0643. Min Act: -0.0001
Data Index: 791633 (C4 (Web Text))
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #19