Model: SoLU Model: 6 Layers, 3072 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3050 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')
Text #0
Max Range: 1.2749. Min Range: -1.2749
Max Act: 1.2618. Min Act: -0.0003
Data Index: 1042146 (C4 (Web Text))
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.2749. Min Range: -1.2749
Max Act: 1.2749. Min Act: -0.0003
Data Index: 1301272 (C4 (Web Text))
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.2749. Min Range: -1.2749
Max Act: 1.2065. Min Act: -0.0003
Data Index: 521597 (C4 (Web Text))
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.2749. Min Range: -1.2749
Max Act: 1.1140. Min Act: -0.0003
Data Index: 940939 (C4 (Web Text))
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.2749. Min Range: -1.2749
Max Act: 1.1961. Min Act: -0.0003
Data Index: 1282257 (C4 (Web Text))
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.2749. Min Range: -1.2749
Max Act: 1.0272. Min Act: -0.0003
Data Index: 1299775 (C4 (Web Text))
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.2749. Min Range: -1.2749
Max Act: 1.0846. Min Act: -0.0003
Data Index: 959390 (C4 (Web Text))
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.2749. Min Range: -1.2749
Max Act: 1.0659. Min Act: -0.0003
Data Index: 37833 (C4 (Web Text))
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.2749. Min Range: -1.2749
Max Act: 1.1243. Min Act: -0.0003
Data Index: 26422 (C4 (Web Text))
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.2749. Min Range: -1.2749
Max Act: 1.0746. Min Act: -0.0003
Data Index: 217791 (C4 (Web Text))
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.2749. Min Range: -1.2749
Max Act: 1.0367. Min Act: -0.0003
Data Index: 1334065 (C4 (Web Text))
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.2749. Min Range: -1.2749
Max Act: 1.0344. Min Act: -0.0003
Data Index: 835415 (C4 (Web Text))
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.2749. Min Range: -1.2749
Max Act: 1.0419. Min Act: -0.0003
Data Index: 683754 (C4 (Web Text))
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.2749. Min Range: -1.2749
Max Act: 1.0312. Min Act: -0.0003
Data Index: 1099706 (C4 (Web Text))
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.2749. Min Range: -1.2749
Max Act: 1.0280. Min Act: -0.0003
Data Index: 392711 (C4 (Web Text))
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.2749. Min Range: -1.2749
Max Act: 0.9314. Min Act: -0.0003
Data Index: 735778 (C4 (Web Text))
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.2749. Min Range: -1.2749
Max Act: 1.0785. Min Act: -0.0003
Data Index: 888734 (C4 (Web Text))
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.2749. Min Range: -1.2749
Max Act: 1.0174. Min Act: -0.0003
Data Index: 858387 (C4 (Web Text))
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.2749. Min Range: -1.2749
Max Act: 1.0143. Min Act: -0.0003
Data Index: 1285076 (C4 (Web Text))
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.2749. Min Range: -1.2749
Max Act: 0.9783. Min Act: -0.0003
Data Index: 658659 (C4 (Web Text))
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #19