Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 821 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 2.5792. Min Range: -2.5792
Max Act: 2.5060. Min Act: -0.0001
Data Index: 1302572 (C4 (Web Text))
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5792. Min Range: -2.5792
Max Act: 2.5792. Min Act: -0.0000
Data Index: 100608 (C4 (Web Text))
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5792. Min Range: -2.5792
Max Act: 2.3630. Min Act: -0.0000
Data Index: 884471 (C4 (Web Text))
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5792. Min Range: -2.5792
Max Act: 2.3415. Min Act: -0.0001
Data Index: 692873 (C4 (Web Text))
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5792. Min Range: -2.5792
Max Act: 2.2320. Min Act: -0.0001
Data Index: 147287 (C4 (Web Text))
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5792. Min Range: -2.5792
Max Act: 2.4723. Min Act: -0.0001
Data Index: 389734 (C4 (Web Text))
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5792. Min Range: -2.5792
Max Act: 2.3314. Min Act: -0.0001
Data Index: 7728 (C4 (Web Text))
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5792. Min Range: -2.5792
Max Act: 2.2295. Min Act: -0.0001
Data Index: 614647 (C4 (Web Text))
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5792. Min Range: -2.5792
Max Act: 2.2247. Min Act: -0.0001
Data Index: 1215180 (C4 (Web Text))
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5792. Min Range: -2.5792
Max Act: 2.2258. Min Act: -0.0001
Data Index: 1249835 (C4 (Web Text))
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5792. Min Range: -2.5792
Max Act: 2.0999. Min Act: -0.0000
Data Index: 1354256 (C4 (Web Text))
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5792. Min Range: -2.5792
Max Act: 2.1964. Min Act: -0.0000
Data Index: 547989 (C4 (Web Text))
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5792. Min Range: -2.5792
Max Act: 2.1968. Min Act: -0.0000
Data Index: 150893 (C4 (Web Text))
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5792. Min Range: -2.5792
Max Act: 2.1926. Min Act: -0.0001
Data Index: 366537 (C4 (Web Text))
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5792. Min Range: -2.5792
Max Act: 2.0767. Min Act: -0.0001
Data Index: 720398 (C4 (Web Text))
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5792. Min Range: -2.5792
Max Act: 2.2963. Min Act: -0.0000
Data Index: 1267560 (C4 (Web Text))
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5792. Min Range: -2.5792
Max Act: 2.1737. Min Act: -0.0001
Data Index: 4622 (C4 (Web Text))
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5792. Min Range: -2.5792
Max Act: 2.0410. Min Act: -0.0001
Data Index: 912017 (C4 (Web Text))
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5792. Min Range: -2.5792
Max Act: 2.1438. Min Act: -0.0001
Data Index: 1070615 (C4 (Web Text))
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5792. Min Range: -2.5792
Max Act: 2.1369. Min Act: -0.0001
Data Index: 178785 (C4 (Web Text))
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #19