Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 20 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 0.9118. Min Range: -0.9118
Max Act: 0.9118. Min Act: -0.0001
Data Index: 584312 (C4 (Web Text))
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.9118. Min Range: -0.9118
Max Act: 0.8470. Min Act: -0.0001
Data Index: 310683 (C4 (Web Text))
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.9118. Min Range: -0.9118
Max Act: 0.8418. Min Act: -0.0001
Data Index: 1277654 (C4 (Web Text))
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.9118. Min Range: -0.9118
Max Act: 0.8737. Min Act: -0.0001
Data Index: 866853 (C4 (Web Text))
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.9118. Min Range: -0.9118
Max Act: 0.8669. Min Act: -0.0001
Data Index: 1287074 (C4 (Web Text))
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.9118. Min Range: -0.9118
Max Act: 0.8925. Min Act: -0.0001
Data Index: 93547 (C4 (Web Text))
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.9118. Min Range: -0.9118
Max Act: 0.8532. Min Act: -0.0001
Data Index: 1149233 (C4 (Web Text))
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.9118. Min Range: -0.9118
Max Act: 0.8083. Min Act: -0.0001
Data Index: 218104 (C4 (Web Text))
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.9118. Min Range: -0.9118
Max Act: 0.7556. Min Act: -0.0001
Data Index: 1283707 (C4 (Web Text))
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.9118. Min Range: -0.9118
Max Act: 0.7820. Min Act: -0.0001
Data Index: 910168 (C4 (Web Text))
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.9118. Min Range: -0.9118
Max Act: 0.8166. Min Act: -0.0001
Data Index: 1280305 (C4 (Web Text))
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.9118. Min Range: -0.9118
Max Act: 0.7950. Min Act: -0.0001
Data Index: 1641591 (Python Code)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.9118. Min Range: -0.9118
Max Act: 0.7610. Min Act: -0.0001
Data Index: 1399843 (Python Code)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.9118. Min Range: -0.9118
Max Act: 0.7424. Min Act: -0.0001
Data Index: 107277 (C4 (Web Text))
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.9118. Min Range: -0.9118
Max Act: 0.7225. Min Act: -0.0001
Data Index: 1102908 (C4 (Web Text))
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.9118. Min Range: -0.9118
Max Act: 0.7113. Min Act: -0.0001
Data Index: 901413 (C4 (Web Text))
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.9118. Min Range: -0.9118
Max Act: 0.7166. Min Act: -0.0001
Data Index: 1110300 (C4 (Web Text))
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.9118. Min Range: -0.9118
Max Act: 0.6850. Min Act: -0.0001
Data Index: 12790 (C4 (Web Text))
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.9118. Min Range: -0.9118
Max Act: 0.7084. Min Act: -0.0001
Data Index: 45153 (C4 (Web Text))
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.9118. Min Range: -0.9118
Max Act: 0.7150. Min Act: -0.0001
Data Index: 1633620 (Python Code)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #19