Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: The Pile
Neuron 4076 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')
Text #0
Max Range: 0.4149. Min Range: -0.4149
Max Act: 0.4149. Min Act: -0.0001
Data Index: 530858 (The Pile)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.4149. Min Range: -0.4149
Max Act: 0.3398. Min Act: -0.0001
Data Index: 1313361 (The Pile)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.4149. Min Range: -0.4149
Max Act: 0.3522. Min Act: -0.0001
Data Index: 11006 (The Pile)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.4149. Min Range: -0.4149
Max Act: 0.3378. Min Act: -0.0001
Data Index: 1128030 (The Pile)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.4149. Min Range: -0.4149
Max Act: 0.2982. Min Act: -0.0001
Data Index: 1146701 (The Pile)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.4149. Min Range: -0.4149
Max Act: 0.3085. Min Act: -0.0001
Data Index: 1014683 (The Pile)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.4149. Min Range: -0.4149
Max Act: 0.3006. Min Act: -0.0001
Data Index: 408520 (The Pile)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.4149. Min Range: -0.4149
Max Act: 0.2904. Min Act: -0.0001
Data Index: 939612 (The Pile)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.4149. Min Range: -0.4149
Max Act: 0.2945. Min Act: -0.0001
Data Index: 1265768 (The Pile)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.4149. Min Range: -0.4149
Max Act: 0.3014. Min Act: -0.0001
Data Index: 1874711 (The Pile)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.4149. Min Range: -0.4149
Max Act: 0.2970. Min Act: -0.0001
Data Index: 1576387 (The Pile)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.4149. Min Range: -0.4149
Max Act: 0.2666. Min Act: -0.0001
Data Index: 877350 (The Pile)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.4149. Min Range: -0.4149
Max Act: 0.2487. Min Act: -0.0001
Data Index: 28964 (The Pile)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.4149. Min Range: -0.4149
Max Act: 0.2872. Min Act: -0.0001
Data Index: 641265 (The Pile)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.4149. Min Range: -0.4149
Max Act: 0.2654. Min Act: -0.0001
Data Index: 1219026 (The Pile)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.4149. Min Range: -0.4149
Max Act: 0.2907. Min Act: -0.0001
Data Index: 348120 (The Pile)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.4149. Min Range: -0.4149
Max Act: 0.2819. Min Act: -0.0001
Data Index: 365363 (The Pile)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.4149. Min Range: -0.4149
Max Act: 0.2644. Min Act: -0.0001
Data Index: 1413498 (The Pile)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.4149. Min Range: -0.4149
Max Act: 0.2806. Min Act: -0.0001
Data Index: 1159942 (The Pile)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.4149. Min Range: -0.4149
Max Act: 0.2538. Min Act: -0.0001
Data Index: 194068 (The Pile)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #19