Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 5497 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 3.5157. Min Range: -3.5157
Max Act: 3.5157. Min Act: -0.0001
Data Index: 677288 (C4 (Web Text))
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5157. Min Range: -3.5157
Max Act: 3.0626. Min Act: -0.0001
Data Index: 964231 (C4 (Web Text))
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5157. Min Range: -3.5157
Max Act: 3.0165. Min Act: -0.0001
Data Index: 784784 (C4 (Web Text))
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5157. Min Range: -3.5157
Max Act: 2.8991. Min Act: -0.0001
Data Index: 708207 (C4 (Web Text))
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5157. Min Range: -3.5157
Max Act: 2.9034. Min Act: -0.0001
Data Index: 1125163 (C4 (Web Text))
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5157. Min Range: -3.5157
Max Act: 2.7341. Min Act: -0.0001
Data Index: 708957 (C4 (Web Text))
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5157. Min Range: -3.5157
Max Act: 2.3520. Min Act: -0.0001
Data Index: 1518570 (Python Code)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5157. Min Range: -3.5157
Max Act: 2.3130. Min Act: -0.0001
Data Index: 319468 (C4 (Web Text))
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5157. Min Range: -3.5157
Max Act: 2.5519. Min Act: -0.0001
Data Index: 1289313 (C4 (Web Text))
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5157. Min Range: -3.5157
Max Act: 2.4799. Min Act: -0.0001
Data Index: 1598634 (Python Code)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5157. Min Range: -3.5157
Max Act: 2.2465. Min Act: -0.0001
Data Index: 1197387 (C4 (Web Text))
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5157. Min Range: -3.5157
Max Act: 2.3462. Min Act: -0.0001
Data Index: 588681 (C4 (Web Text))
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5157. Min Range: -3.5157
Max Act: 2.1626. Min Act: -0.0001
Data Index: 368127 (C4 (Web Text))
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5157. Min Range: -3.5157
Max Act: 2.1701. Min Act: -0.0001
Data Index: 707597 (C4 (Web Text))
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5157. Min Range: -3.5157
Max Act: 1.9822. Min Act: -0.0001
Data Index: 1083024 (C4 (Web Text))
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5157. Min Range: -3.5157
Max Act: 2.1032. Min Act: -0.0001
Data Index: 1169876 (C4 (Web Text))
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5157. Min Range: -3.5157
Max Act: 2.1800. Min Act: -0.0001
Data Index: 12076 (C4 (Web Text))
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5157. Min Range: -3.5157
Max Act: 2.0887. Min Act: -0.0001
Data Index: 843315 (C4 (Web Text))
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5157. Min Range: -3.5157
Max Act: 1.9827. Min Act: -0.0001
Data Index: 388108 (C4 (Web Text))
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5157. Min Range: -3.5157
Max Act: 2.0807. Min Act: -0.0001
Data Index: 99071 (C4 (Web Text))
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #19