Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: The Pile
Neuron 2291 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')
Text #0
Max Range: 1.7274. Min Range: -1.7274
Max Act: 1.7198. Min Act: -0.0000
Data Index: 83404 (The Pile)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.7274. Min Range: -1.7274
Max Act: 1.7274. Min Act: -0.0000
Data Index: 952701 (The Pile)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.7274. Min Range: -1.7274
Max Act: 1.5705. Min Act: -0.0000
Data Index: 1114629 (The Pile)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.7274. Min Range: -1.7274
Max Act: 1.5135. Min Act: -0.0000
Data Index: 1611941 (The Pile)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.7274. Min Range: -1.7274
Max Act: 1.4870. Min Act: -0.0000
Data Index: 280868 (The Pile)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.7274. Min Range: -1.7274
Max Act: 1.4907. Min Act: -0.0000
Data Index: 1088138 (The Pile)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.7274. Min Range: -1.7274
Max Act: 1.3942. Min Act: -0.0000
Data Index: 922422 (The Pile)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.7274. Min Range: -1.7274
Max Act: 1.4632. Min Act: -0.0000
Data Index: 94 (The Pile)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.7274. Min Range: -1.7274
Max Act: 1.2854. Min Act: -0.0000
Data Index: 1067736 (The Pile)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.7274. Min Range: -1.7274
Max Act: 1.2714. Min Act: -0.0000
Data Index: 94135 (The Pile)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.7274. Min Range: -1.7274
Max Act: 1.2847. Min Act: -0.0000
Data Index: 1634775 (The Pile)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.7274. Min Range: -1.7274
Max Act: 1.4103. Min Act: -0.0000
Data Index: 1104165 (The Pile)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.7274. Min Range: -1.7274
Max Act: 1.5556. Min Act: -0.0000
Data Index: 1302610 (The Pile)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.7274. Min Range: -1.7274
Max Act: 1.1384. Min Act: -0.0000
Data Index: 896174 (The Pile)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.7274. Min Range: -1.7274
Max Act: 1.3529. Min Act: -0.0000
Data Index: 1043104 (The Pile)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.7274. Min Range: -1.7274
Max Act: 1.2541. Min Act: -0.0000
Data Index: 447006 (The Pile)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.7274. Min Range: -1.7274
Max Act: 1.3280. Min Act: -0.0000
Data Index: 258260 (The Pile)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.7274. Min Range: -1.7274
Max Act: 1.2425. Min Act: -0.0000
Data Index: 1220485 (The Pile)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.7274. Min Range: -1.7274
Max Act: 1.1606. Min Act: -0.0000
Data Index: 1645000 (The Pile)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.7274. Min Range: -1.7274
Max Act: 1.2137. Min Act: -0.0000
Data Index: 1315866 (The Pile)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #19