Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3369 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 2.8551. Min Range: -2.8551
Max Act: 2.8551. Min Act: -0.0000
Data Index: 45631 (C4 (Web Text))
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8551. Min Range: -2.8551
Max Act: 2.8314. Min Act: -0.0001
Data Index: 487181 (C4 (Web Text))
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8551. Min Range: -2.8551
Max Act: 2.5629. Min Act: -0.0001
Data Index: 220249 (C4 (Web Text))
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8551. Min Range: -2.8551
Max Act: 2.7272. Min Act: -0.0000
Data Index: 517029 (C4 (Web Text))
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8551. Min Range: -2.8551
Max Act: 2.5790. Min Act: -0.0001
Data Index: 296281 (C4 (Web Text))
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8551. Min Range: -2.8551
Max Act: 2.5881. Min Act: -0.0001
Data Index: 46119 (C4 (Web Text))
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8551. Min Range: -2.8551
Max Act: 2.5373. Min Act: -0.0001
Data Index: 220882 (C4 (Web Text))
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8551. Min Range: -2.8551
Max Act: 2.4029. Min Act: -0.0001
Data Index: 192881 (C4 (Web Text))
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8551. Min Range: -2.8551
Max Act: 2.5498. Min Act: -0.0001
Data Index: 999627 (C4 (Web Text))
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8551. Min Range: -2.8551
Max Act: 2.1534. Min Act: -0.0001
Data Index: 737997 (C4 (Web Text))
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8551. Min Range: -2.8551
Max Act: 2.2477. Min Act: -0.0001
Data Index: 827697 (C4 (Web Text))
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8551. Min Range: -2.8551
Max Act: 2.3626. Min Act: -0.0001
Data Index: 1050578 (C4 (Web Text))
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8551. Min Range: -2.8551
Max Act: 2.2041. Min Act: -0.0000
Data Index: 365488 (C4 (Web Text))
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8551. Min Range: -2.8551
Max Act: 2.3101. Min Act: -0.0001
Data Index: 538790 (C4 (Web Text))
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8551. Min Range: -2.8551
Max Act: 2.5373. Min Act: -0.0001
Data Index: 1147754 (C4 (Web Text))
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8551. Min Range: -2.8551
Max Act: 2.2800. Min Act: -0.0001
Data Index: 738364 (C4 (Web Text))
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8551. Min Range: -2.8551
Max Act: 2.1258. Min Act: -0.0001
Data Index: 882089 (C4 (Web Text))
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8551. Min Range: -2.8551
Max Act: 2.2205. Min Act: -0.0001
Data Index: 427923 (C4 (Web Text))
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8551. Min Range: -2.8551
Max Act: 2.3380. Min Act: -0.0001
Data Index: 902060 (C4 (Web Text))
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8551. Min Range: -2.8551
Max Act: 2.1888. Min Act: -0.0000
Data Index: 1056472 (C4 (Web Text))
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #19