Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3412 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 2.7684. Min Range: -2.7684
Max Act: 2.7684. Min Act: -0.0001
Data Index: 836646 (C4 (Web Text))
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7684. Min Range: -2.7684
Max Act: 2.7214. Min Act: -0.0001
Data Index: 752132 (C4 (Web Text))
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7684. Min Range: -2.7684
Max Act: 2.2595. Min Act: -0.0001
Data Index: 190538 (C4 (Web Text))
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7684. Min Range: -2.7684
Max Act: 2.2860. Min Act: -0.0001
Data Index: 436421 (C4 (Web Text))
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7684. Min Range: -2.7684
Max Act: 2.4917. Min Act: -0.0001
Data Index: 1135839 (C4 (Web Text))
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7684. Min Range: -2.7684
Max Act: 2.2581. Min Act: -0.0001
Data Index: 768395 (C4 (Web Text))
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7684. Min Range: -2.7684
Max Act: 2.3379. Min Act: -0.0001
Data Index: 112394 (C4 (Web Text))
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7684. Min Range: -2.7684
Max Act: 2.2081. Min Act: -0.0001
Data Index: 264844 (C4 (Web Text))
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7684. Min Range: -2.7684
Max Act: 2.3140. Min Act: -0.0001
Data Index: 77629 (C4 (Web Text))
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7684. Min Range: -2.7684
Max Act: 2.2715. Min Act: -0.0001
Data Index: 281646 (C4 (Web Text))
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7684. Min Range: -2.7684
Max Act: 2.2579. Min Act: -0.0001
Data Index: 221102 (C4 (Web Text))
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7684. Min Range: -2.7684
Max Act: 1.9487. Min Act: -0.0001
Data Index: 42390 (C4 (Web Text))
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7684. Min Range: -2.7684
Max Act: 2.0871. Min Act: -0.0001
Data Index: 904606 (C4 (Web Text))
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7684. Min Range: -2.7684
Max Act: 2.1960. Min Act: -0.0001
Data Index: 250056 (C4 (Web Text))
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7684. Min Range: -2.7684
Max Act: 2.1813. Min Act: -0.0001
Data Index: 864994 (C4 (Web Text))
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7684. Min Range: -2.7684
Max Act: 2.1880. Min Act: -0.0001
Data Index: 252276 (C4 (Web Text))
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7684. Min Range: -2.7684
Max Act: 2.1817. Min Act: -0.0001
Data Index: 689051 (C4 (Web Text))
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7684. Min Range: -2.7684
Max Act: 2.2278. Min Act: -0.0001
Data Index: 1313097 (C4 (Web Text))
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7684. Min Range: -2.7684
Max Act: 2.2797. Min Act: -0.0001
Data Index: 734248 (C4 (Web Text))
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7684. Min Range: -2.7684
Max Act: 2.2553. Min Act: -0.0001
Data Index: 970860 (C4 (Web Text))
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #19