Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3093 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 1.9646. Min Range: -1.9646
Max Act: 1.7642. Min Act: -0.0001
Data Index: 312827 (C4 (Web Text))
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.9646. Min Range: -1.9646
Max Act: 1.9646. Min Act: -0.0001
Data Index: 578058 (C4 (Web Text))
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.9646. Min Range: -1.9646
Max Act: 1.6024. Min Act: -0.0001
Data Index: 1220785 (C4 (Web Text))
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.9646. Min Range: -1.9646
Max Act: 1.5587. Min Act: -0.0001
Data Index: 1251781 (C4 (Web Text))
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.9646. Min Range: -1.9646
Max Act: 1.5125. Min Act: -0.0001
Data Index: 779613 (C4 (Web Text))
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.9646. Min Range: -1.9646
Max Act: 1.3662. Min Act: -0.0001
Data Index: 69125 (C4 (Web Text))
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.9646. Min Range: -1.9646
Max Act: 1.2652. Min Act: -0.0001
Data Index: 1655979 (Python Code)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.9646. Min Range: -1.9646
Max Act: 1.2500. Min Act: -0.0001
Data Index: 1581639 (Python Code)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.9646. Min Range: -1.9646
Max Act: 1.4228. Min Act: -0.0001
Data Index: 756639 (C4 (Web Text))
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.9646. Min Range: -1.9646
Max Act: 1.3075. Min Act: -0.0001
Data Index: 132616 (C4 (Web Text))
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.9646. Min Range: -1.9646
Max Act: 1.1500. Min Act: -0.0001
Data Index: 307348 (C4 (Web Text))
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.9646. Min Range: -1.9646
Max Act: 1.3099. Min Act: -0.0001
Data Index: 219972 (C4 (Web Text))
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.9646. Min Range: -1.9646
Max Act: 1.2772. Min Act: -0.0001
Data Index: 1584719 (Python Code)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.9646. Min Range: -1.9646
Max Act: 1.2677. Min Act: -0.0001
Data Index: 94093 (C4 (Web Text))
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.9646. Min Range: -1.9646
Max Act: 1.3286. Min Act: -0.0001
Data Index: 1071223 (C4 (Web Text))
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.9646. Min Range: -1.9646
Max Act: 1.2529. Min Act: -0.0001
Data Index: 1553891 (Python Code)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.9646. Min Range: -1.9646
Max Act: 1.2711. Min Act: -0.0001
Data Index: 1406331 (Python Code)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.9646. Min Range: -1.9646
Max Act: 1.2143. Min Act: -0.0001
Data Index: 1119759 (C4 (Web Text))
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.9646. Min Range: -1.9646
Max Act: 1.1168. Min Act: -0.0001
Data Index: 1559131 (Python Code)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.9646. Min Range: -1.9646
Max Act: 1.1297. Min Act: -0.0001
Data Index: 900010 (C4 (Web Text))
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #19