Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3685 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 2.7822. Min Range: -2.7822
Max Act: 2.7822. Min Act: -0.0001
Data Index: 1066083 (C4 (Web Text))
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7822. Min Range: -2.7822
Max Act: 2.5771. Min Act: -0.0001
Data Index: 1302224 (C4 (Web Text))
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7822. Min Range: -2.7822
Max Act: 2.4695. Min Act: -0.0001
Data Index: 304702 (C4 (Web Text))
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7822. Min Range: -2.7822
Max Act: 2.2742. Min Act: -0.0001
Data Index: 1351567 (C4 (Web Text))
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7822. Min Range: -2.7822
Max Act: 2.2677. Min Act: -0.0000
Data Index: 177353 (C4 (Web Text))
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7822. Min Range: -2.7822
Max Act: 2.1352. Min Act: -0.0000
Data Index: 561704 (C4 (Web Text))
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7822. Min Range: -2.7822
Max Act: 2.2291. Min Act: -0.0001
Data Index: 414110 (C4 (Web Text))
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7822. Min Range: -2.7822
Max Act: 2.1513. Min Act: -0.0001
Data Index: 471372 (C4 (Web Text))
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7822. Min Range: -2.7822
Max Act: 2.1855. Min Act: -0.0001
Data Index: 658361 (C4 (Web Text))
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7822. Min Range: -2.7822
Max Act: 2.0587. Min Act: -0.0001
Data Index: 1284868 (C4 (Web Text))
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7822. Min Range: -2.7822
Max Act: 2.1938. Min Act: -0.0001
Data Index: 47808 (C4 (Web Text))
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7822. Min Range: -2.7822
Max Act: 2.0412. Min Act: -0.0001
Data Index: 44339 (C4 (Web Text))
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7822. Min Range: -2.7822
Max Act: 1.8290. Min Act: -0.0001
Data Index: 297392 (C4 (Web Text))
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7822. Min Range: -2.7822
Max Act: 1.9750. Min Act: -0.0001
Data Index: 364233 (C4 (Web Text))
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7822. Min Range: -2.7822
Max Act: 1.9640. Min Act: -0.0001
Data Index: 888260 (C4 (Web Text))
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7822. Min Range: -2.7822
Max Act: 2.1395. Min Act: -0.0001
Data Index: 1098527 (C4 (Web Text))
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7822. Min Range: -2.7822
Max Act: 2.0078. Min Act: -0.0001
Data Index: 445042 (C4 (Web Text))
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7822. Min Range: -2.7822
Max Act: 2.0995. Min Act: -0.0001
Data Index: 797255 (C4 (Web Text))
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7822. Min Range: -2.7822
Max Act: 2.1026. Min Act: -0.0001
Data Index: 1521 (C4 (Web Text))
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7822. Min Range: -2.7822
Max Act: 1.9784. Min Act: -0.0001
Data Index: 813188 (C4 (Web Text))
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #19