Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 307 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 2.6647. Min Range: -2.6647
Max Act: 2.6197. Min Act: -0.0001
Data Index: 295306 (C4 (Web Text))
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6647. Min Range: -2.6647
Max Act: 2.5782. Min Act: -0.0001
Data Index: 251643 (C4 (Web Text))
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6647. Min Range: -2.6647
Max Act: 2.6647. Min Act: -0.0001
Data Index: 190898 (C4 (Web Text))
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6647. Min Range: -2.6647
Max Act: 2.4836. Min Act: -0.0001
Data Index: 585931 (C4 (Web Text))
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6647. Min Range: -2.6647
Max Act: 2.3548. Min Act: -0.0001
Data Index: 227553 (C4 (Web Text))
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6647. Min Range: -2.6647
Max Act: 2.2333. Min Act: -0.0001
Data Index: 1325059 (C4 (Web Text))
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6647. Min Range: -2.6647
Max Act: 2.2182. Min Act: -0.0001
Data Index: 179132 (C4 (Web Text))
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6647. Min Range: -2.6647
Max Act: 2.2298. Min Act: -0.0001
Data Index: 407261 (C4 (Web Text))
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6647. Min Range: -2.6647
Max Act: 2.0992. Min Act: -0.0001
Data Index: 262331 (C4 (Web Text))
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6647. Min Range: -2.6647
Max Act: 2.1743. Min Act: -0.0001
Data Index: 370406 (C4 (Web Text))
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6647. Min Range: -2.6647
Max Act: 2.1531. Min Act: -0.0001
Data Index: 441491 (C4 (Web Text))
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6647. Min Range: -2.6647
Max Act: 2.0562. Min Act: -0.0001
Data Index: 76604 (C4 (Web Text))
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6647. Min Range: -2.6647
Max Act: 1.9340. Min Act: -0.0001
Data Index: 486094 (C4 (Web Text))
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6647. Min Range: -2.6647
Max Act: 1.7428. Min Act: -0.0001
Data Index: 698477 (C4 (Web Text))
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6647. Min Range: -2.6647
Max Act: 1.8159. Min Act: -0.0001
Data Index: 468036 (C4 (Web Text))
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6647. Min Range: -2.6647
Max Act: 1.7131. Min Act: -0.0001
Data Index: 347424 (C4 (Web Text))
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6647. Min Range: -2.6647
Max Act: 1.6137. Min Act: -0.0001
Data Index: 272 (C4 (Web Text))
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6647. Min Range: -2.6647
Max Act: 1.7031. Min Act: -0.0001
Data Index: 1340213 (C4 (Web Text))
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6647. Min Range: -2.6647
Max Act: 1.5504. Min Act: -0.0001
Data Index: 1228922 (C4 (Web Text))
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6647. Min Range: -2.6647
Max Act: 1.5238. Min Act: -0.0001
Data Index: 799716 (C4 (Web Text))
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #19