Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2137 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 1.8922. Min Range: -1.8922
Max Act: 1.8922. Min Act: -0.0001
Data Index: 503461 (C4 (Web Text))
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.8922. Min Range: -1.8922
Max Act: 1.8498. Min Act: -0.0001
Data Index: 364385 (C4 (Web Text))
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.8922. Min Range: -1.8922
Max Act: 1.6887. Min Act: -0.0001
Data Index: 1418041 (Python Code)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.8922. Min Range: -1.8922
Max Act: 1.6217. Min Act: -0.0001
Data Index: 957484 (C4 (Web Text))
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.8922. Min Range: -1.8922
Max Act: 1.5336. Min Act: -0.0001
Data Index: 894435 (C4 (Web Text))
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.8922. Min Range: -1.8922
Max Act: 1.7895. Min Act: -0.0001
Data Index: 1074021 (C4 (Web Text))
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.8922. Min Range: -1.8922
Max Act: 1.5679. Min Act: -0.0001
Data Index: 1142713 (C4 (Web Text))
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.8922. Min Range: -1.8922
Max Act: 1.6572. Min Act: -0.0001
Data Index: 1296319 (C4 (Web Text))
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.8922. Min Range: -1.8922
Max Act: 1.6521. Min Act: -0.0001
Data Index: 279405 (C4 (Web Text))
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.8922. Min Range: -1.8922
Max Act: 1.5609. Min Act: -0.0001
Data Index: 887567 (C4 (Web Text))
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.8922. Min Range: -1.8922
Max Act: 1.5990. Min Act: -0.0001
Data Index: 327085 (C4 (Web Text))
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.8922. Min Range: -1.8922
Max Act: 1.5923. Min Act: -0.0001
Data Index: 512582 (C4 (Web Text))
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.8922. Min Range: -1.8922
Max Act: 1.5513. Min Act: -0.0001
Data Index: 1317982 (C4 (Web Text))
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.8922. Min Range: -1.8922
Max Act: 1.5335. Min Act: -0.0001
Data Index: 739318 (C4 (Web Text))
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.8922. Min Range: -1.8922
Max Act: 1.2850. Min Act: -0.0001
Data Index: 854086 (C4 (Web Text))
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.8922. Min Range: -1.8922
Max Act: 1.3668. Min Act: -0.0001
Data Index: 21928 (C4 (Web Text))
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.8922. Min Range: -1.8922
Max Act: 1.4933. Min Act: -0.0001
Data Index: 644763 (C4 (Web Text))
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.8922. Min Range: -1.8922
Max Act: 1.4189. Min Act: -0.0001
Data Index: 1039384 (C4 (Web Text))
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.8922. Min Range: -1.8922
Max Act: 1.1885. Min Act: -0.0001
Data Index: 1609346 (Python Code)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.8922. Min Range: -1.8922
Max Act: 1.4732. Min Act: -0.0001
Data Index: 864994 (C4 (Web Text))
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #19