Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3016 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 1.7832. Min Range: -1.7832
Max Act: 1.7832. Min Act: -0.0001
Data Index: 615467 (C4 (Web Text))
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.7832. Min Range: -1.7832
Max Act: 1.5293. Min Act: -0.0001
Data Index: 866159 (C4 (Web Text))
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.7832. Min Range: -1.7832
Max Act: 1.4712. Min Act: -0.0001
Data Index: 588773 (C4 (Web Text))
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.7832. Min Range: -1.7832
Max Act: 1.2997. Min Act: -0.0001
Data Index: 277088 (C4 (Web Text))
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.7832. Min Range: -1.7832
Max Act: 1.3855. Min Act: -0.0001
Data Index: 494340 (C4 (Web Text))
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.7832. Min Range: -1.7832
Max Act: 1.2954. Min Act: -0.0001
Data Index: 91821 (C4 (Web Text))
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.7832. Min Range: -1.7832
Max Act: 1.3637. Min Act: -0.0001
Data Index: 845272 (C4 (Web Text))
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.7832. Min Range: -1.7832
Max Act: 1.2785. Min Act: -0.0001
Data Index: 663027 (C4 (Web Text))
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.7832. Min Range: -1.7832
Max Act: 1.2307. Min Act: -0.0001
Data Index: 1132706 (C4 (Web Text))
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.7832. Min Range: -1.7832
Max Act: 1.2728. Min Act: -0.0001
Data Index: 1242260 (C4 (Web Text))
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.7832. Min Range: -1.7832
Max Act: 1.0505. Min Act: -0.0001
Data Index: 23441 (C4 (Web Text))
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.7832. Min Range: -1.7832
Max Act: 1.1658. Min Act: -0.0001
Data Index: 179090 (C4 (Web Text))
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.7832. Min Range: -1.7832
Max Act: 1.1549. Min Act: -0.0001
Data Index: 582320 (C4 (Web Text))
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.7832. Min Range: -1.7832
Max Act: 1.1552. Min Act: -0.0001
Data Index: 179478 (C4 (Web Text))
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.7832. Min Range: -1.7832
Max Act: 1.2455. Min Act: -0.0001
Data Index: 293007 (C4 (Web Text))
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.7832. Min Range: -1.7832
Max Act: 0.9937. Min Act: -0.0001
Data Index: 940608 (C4 (Web Text))
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.7832. Min Range: -1.7832
Max Act: 1.1771. Min Act: -0.0001
Data Index: 1347402 (C4 (Web Text))
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.7832. Min Range: -1.7832
Max Act: 1.1871. Min Act: -0.0001
Data Index: 436084 (C4 (Web Text))
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.7832. Min Range: -1.7832
Max Act: 1.1302. Min Act: -0.0001
Data Index: 1176489 (C4 (Web Text))
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.7832. Min Range: -1.7832
Max Act: 1.1564. Min Act: -0.0001
Data Index: 987593 (C4 (Web Text))
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #19