Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 4072 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 2.1181. Min Range: -2.1181
Max Act: 2.1181. Min Act: -0.0001
Data Index: 118427 (C4 (Web Text))
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.1181. Min Range: -2.1181
Max Act: 1.8878. Min Act: -0.0001
Data Index: 594984 (C4 (Web Text))
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.1181. Min Range: -2.1181
Max Act: 1.6506. Min Act: -0.0001
Data Index: 1081167 (C4 (Web Text))
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.1181. Min Range: -2.1181
Max Act: 1.5153. Min Act: -0.0000
Data Index: 450965 (C4 (Web Text))
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.1181. Min Range: -2.1181
Max Act: 1.4203. Min Act: -0.0001
Data Index: 1006376 (C4 (Web Text))
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.1181. Min Range: -2.1181
Max Act: 1.4904. Min Act: -0.0001
Data Index: 677988 (C4 (Web Text))
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.1181. Min Range: -2.1181
Max Act: 1.3644. Min Act: -0.0001
Data Index: 685754 (C4 (Web Text))
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.1181. Min Range: -2.1181
Max Act: 1.4885. Min Act: -0.0001
Data Index: 791061 (C4 (Web Text))
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.1181. Min Range: -2.1181
Max Act: 1.4237. Min Act: -0.0001
Data Index: 869974 (C4 (Web Text))
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.1181. Min Range: -2.1181
Max Act: 1.2945. Min Act: -0.0001
Data Index: 794947 (C4 (Web Text))
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.1181. Min Range: -2.1181
Max Act: 1.2077. Min Act: -0.0001
Data Index: 1188884 (C4 (Web Text))
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.1181. Min Range: -2.1181
Max Act: 1.3543. Min Act: -0.0001
Data Index: 665857 (C4 (Web Text))
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.1181. Min Range: -2.1181
Max Act: 1.3433. Min Act: -0.0001
Data Index: 507673 (C4 (Web Text))
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.1181. Min Range: -2.1181
Max Act: 1.3268. Min Act: -0.0001
Data Index: 643422 (C4 (Web Text))
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.1181. Min Range: -2.1181
Max Act: 1.4141. Min Act: -0.0001
Data Index: 1321071 (C4 (Web Text))
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.1181. Min Range: -2.1181
Max Act: 1.1751. Min Act: -0.0001
Data Index: 824573 (C4 (Web Text))
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.1181. Min Range: -2.1181
Max Act: 1.2794. Min Act: -0.0001
Data Index: 1226210 (C4 (Web Text))
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.1181. Min Range: -2.1181
Max Act: 1.0622. Min Act: -0.0001
Data Index: 507526 (C4 (Web Text))
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.1181. Min Range: -2.1181
Max Act: 1.3054. Min Act: -0.0001
Data Index: 1175099 (C4 (Web Text))
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.1181. Min Range: -2.1181
Max Act: 1.3632. Min Act: -0.0001
Data Index: 179483 (C4 (Web Text))
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #19