Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3470 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 2.5890. Min Range: -2.5890
Max Act: 2.5890. Min Act: -0.0001
Data Index: 167235 (C4 (Web Text))
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5890. Min Range: -2.5890
Max Act: 2.1033. Min Act: -0.0001
Data Index: 645018 (C4 (Web Text))
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5890. Min Range: -2.5890
Max Act: 1.9085. Min Act: -0.0001
Data Index: 748787 (C4 (Web Text))
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5890. Min Range: -2.5890
Max Act: 2.0230. Min Act: -0.0001
Data Index: 546412 (C4 (Web Text))
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5890. Min Range: -2.5890
Max Act: 2.1205. Min Act: -0.0001
Data Index: 1636962 (Python Code)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5890. Min Range: -2.5890
Max Act: 2.0517. Min Act: -0.0001
Data Index: 441139 (C4 (Web Text))
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5890. Min Range: -2.5890
Max Act: 2.1105. Min Act: -0.0001
Data Index: 470914 (C4 (Web Text))
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5890. Min Range: -2.5890
Max Act: 2.0409. Min Act: -0.0001
Data Index: 56609 (C4 (Web Text))
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5890. Min Range: -2.5890
Max Act: 2.1817. Min Act: -0.0001
Data Index: 572941 (C4 (Web Text))
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5890. Min Range: -2.5890
Max Act: 2.1006. Min Act: -0.0001
Data Index: 381356 (C4 (Web Text))
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5890. Min Range: -2.5890
Max Act: 2.0438. Min Act: -0.0001
Data Index: 1256917 (C4 (Web Text))
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5890. Min Range: -2.5890
Max Act: 1.8338. Min Act: -0.0001
Data Index: 16394 (C4 (Web Text))
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5890. Min Range: -2.5890
Max Act: 2.0521. Min Act: -0.0001
Data Index: 1174512 (C4 (Web Text))
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5890. Min Range: -2.5890
Max Act: 2.0494. Min Act: -0.0001
Data Index: 558755 (C4 (Web Text))
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5890. Min Range: -2.5890
Max Act: 1.8234. Min Act: -0.0001
Data Index: 836468 (C4 (Web Text))
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5890. Min Range: -2.5890
Max Act: 1.9148. Min Act: -0.0001
Data Index: 1589005 (Python Code)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5890. Min Range: -2.5890
Max Act: 1.8540. Min Act: -0.0001
Data Index: 181356 (C4 (Web Text))
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5890. Min Range: -2.5890
Max Act: 1.8902. Min Act: -0.0001
Data Index: 885242 (C4 (Web Text))
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5890. Min Range: -2.5890
Max Act: 1.8954. Min Act: -0.0001
Data Index: 421479 (C4 (Web Text))
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5890. Min Range: -2.5890
Max Act: 1.9302. Min Act: -0.0001
Data Index: 153389 (C4 (Web Text))
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #19