Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2651 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 1.7288. Min Range: -1.7288
Max Act: 1.7288. Min Act: -0.0001
Data Index: 975654 (C4 (Web Text))
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.7288. Min Range: -1.7288
Max Act: 1.5400. Min Act: -0.0001
Data Index: 396095 (C4 (Web Text))
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.7288. Min Range: -1.7288
Max Act: 1.3880. Min Act: -0.0001
Data Index: 176226 (C4 (Web Text))
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.7288. Min Range: -1.7288
Max Act: 1.2155. Min Act: -0.0001
Data Index: 386907 (C4 (Web Text))
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.7288. Min Range: -1.7288
Max Act: 1.2346. Min Act: -0.0001
Data Index: 1334882 (C4 (Web Text))
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.7288. Min Range: -1.7288
Max Act: 1.3435. Min Act: -0.0001
Data Index: 1242027 (C4 (Web Text))
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.7288. Min Range: -1.7288
Max Act: 1.2303. Min Act: -0.0001
Data Index: 1095158 (C4 (Web Text))
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.7288. Min Range: -1.7288
Max Act: 1.1586. Min Act: -0.0001
Data Index: 547750 (C4 (Web Text))
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.7288. Min Range: -1.7288
Max Act: 1.3049. Min Act: -0.0001
Data Index: 1296085 (C4 (Web Text))
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.7288. Min Range: -1.7288
Max Act: 1.1354. Min Act: -0.0001
Data Index: 370883 (C4 (Web Text))
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.7288. Min Range: -1.7288
Max Act: 1.1928. Min Act: -0.0001
Data Index: 1040135 (C4 (Web Text))
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.7288. Min Range: -1.7288
Max Act: 1.2385. Min Act: -0.0001
Data Index: 1085414 (C4 (Web Text))
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.7288. Min Range: -1.7288
Max Act: 1.1353. Min Act: -0.0001
Data Index: 721893 (C4 (Web Text))
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.7288. Min Range: -1.7288
Max Act: 1.1367. Min Act: -0.0001
Data Index: 1214627 (C4 (Web Text))
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.7288. Min Range: -1.7288
Max Act: 1.1420. Min Act: -0.0001
Data Index: 1128410 (C4 (Web Text))
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.7288. Min Range: -1.7288
Max Act: 1.0666. Min Act: -0.0001
Data Index: 1277629 (C4 (Web Text))
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.7288. Min Range: -1.7288
Max Act: 1.1554. Min Act: -0.0001
Data Index: 45084 (C4 (Web Text))
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.7288. Min Range: -1.7288
Max Act: 1.0656. Min Act: -0.0001
Data Index: 528936 (C4 (Web Text))
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.7288. Min Range: -1.7288
Max Act: 1.0807. Min Act: -0.0001
Data Index: 58868 (C4 (Web Text))
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.7288. Min Range: -1.7288
Max Act: 1.1030. Min Act: -0.0001
Data Index: 100061 (C4 (Web Text))
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #19