Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3558 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 2.7386. Min Range: -2.7386
Max Act: 2.7386. Min Act: -0.0001
Data Index: 507364 (C4 (Web Text))
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7386. Min Range: -2.7386
Max Act: 2.7116. Min Act: -0.0001
Data Index: 994115 (C4 (Web Text))
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7386. Min Range: -2.7386
Max Act: 2.6567. Min Act: -0.0001
Data Index: 939527 (C4 (Web Text))
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7386. Min Range: -2.7386
Max Act: 2.4466. Min Act: -0.0001
Data Index: 1140036 (C4 (Web Text))
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7386. Min Range: -2.7386
Max Act: 2.4617. Min Act: -0.0001
Data Index: 496512 (C4 (Web Text))
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7386. Min Range: -2.7386
Max Act: 2.3311. Min Act: -0.0001
Data Index: 928599 (C4 (Web Text))
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7386. Min Range: -2.7386
Max Act: 2.4565. Min Act: -0.0001
Data Index: 355840 (C4 (Web Text))
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7386. Min Range: -2.7386
Max Act: 2.3025. Min Act: -0.0001
Data Index: 190910 (C4 (Web Text))
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7386. Min Range: -2.7386
Max Act: 2.3118. Min Act: -0.0001
Data Index: 1254288 (C4 (Web Text))
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7386. Min Range: -2.7386
Max Act: 2.3162. Min Act: -0.0001
Data Index: 415427 (C4 (Web Text))
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7386. Min Range: -2.7386
Max Act: 2.2864. Min Act: -0.0001
Data Index: 372011 (C4 (Web Text))
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7386. Min Range: -2.7386
Max Act: 2.4261. Min Act: -0.0001
Data Index: 1293604 (C4 (Web Text))
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7386. Min Range: -2.7386
Max Act: 2.4129. Min Act: -0.0001
Data Index: 961135 (C4 (Web Text))
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7386. Min Range: -2.7386
Max Act: 2.2953. Min Act: -0.0001
Data Index: 1316514 (C4 (Web Text))
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7386. Min Range: -2.7386
Max Act: 2.4155. Min Act: -0.0001
Data Index: 362870 (C4 (Web Text))
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7386. Min Range: -2.7386
Max Act: 2.2860. Min Act: -0.0001
Data Index: 204837 (C4 (Web Text))
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7386. Min Range: -2.7386
Max Act: 2.2679. Min Act: -0.0001
Data Index: 713597 (C4 (Web Text))
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7386. Min Range: -2.7386
Max Act: 2.3713. Min Act: -0.0001
Data Index: 34391 (C4 (Web Text))
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7386. Min Range: -2.7386
Max Act: 2.1350. Min Act: -0.0001
Data Index: 42020 (C4 (Web Text))
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7386. Min Range: -2.7386
Max Act: 2.2398. Min Act: -0.0001
Data Index: 1198776 (C4 (Web Text))
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #19