Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2336 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 1.3054. Min Range: -1.3054
Max Act: 1.3054. Min Act: -0.0001
Data Index: 430061 (C4 (Web Text))
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.3054. Min Range: -1.3054
Max Act: 1.2174. Min Act: -0.0001
Data Index: 213158 (C4 (Web Text))
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.3054. Min Range: -1.3054
Max Act: 1.2043. Min Act: -0.0001
Data Index: 168107 (C4 (Web Text))
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.3054. Min Range: -1.3054
Max Act: 1.1322. Min Act: -0.0001
Data Index: 1284943 (C4 (Web Text))
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.3054. Min Range: -1.3054
Max Act: 1.0325. Min Act: -0.0001
Data Index: 739717 (C4 (Web Text))
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.3054. Min Range: -1.3054
Max Act: 1.0858. Min Act: -0.0001
Data Index: 285822 (C4 (Web Text))
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.3054. Min Range: -1.3054
Max Act: 1.0469. Min Act: -0.0001
Data Index: 676068 (C4 (Web Text))
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.3054. Min Range: -1.3054
Max Act: 1.0648. Min Act: -0.0001
Data Index: 563702 (C4 (Web Text))
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.3054. Min Range: -1.3054
Max Act: 1.0658. Min Act: -0.0001
Data Index: 1057887 (C4 (Web Text))
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.3054. Min Range: -1.3054
Max Act: 0.9633. Min Act: -0.0001
Data Index: 826785 (C4 (Web Text))
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.3054. Min Range: -1.3054
Max Act: 0.9488. Min Act: -0.0001
Data Index: 411143 (C4 (Web Text))
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.3054. Min Range: -1.3054
Max Act: 0.9805. Min Act: -0.0001
Data Index: 507303 (C4 (Web Text))
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.3054. Min Range: -1.3054
Max Act: 1.0011. Min Act: -0.0001
Data Index: 576426 (C4 (Web Text))
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.3054. Min Range: -1.3054
Max Act: 0.9868. Min Act: -0.0001
Data Index: 993375 (C4 (Web Text))
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.3054. Min Range: -1.3054
Max Act: 1.0465. Min Act: -0.0001
Data Index: 596364 (C4 (Web Text))
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.3054. Min Range: -1.3054
Max Act: 0.9527. Min Act: -0.0001
Data Index: 674934 (C4 (Web Text))
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.3054. Min Range: -1.3054
Max Act: 0.8693. Min Act: -0.0001
Data Index: 606356 (C4 (Web Text))
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.3054. Min Range: -1.3054
Max Act: 0.9196. Min Act: -0.0001
Data Index: 52116 (C4 (Web Text))
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.3054. Min Range: -1.3054
Max Act: 0.9117. Min Act: -0.0001
Data Index: 1084466 (C4 (Web Text))
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.3054. Min Range: -1.3054
Max Act: 0.9291. Min Act: -0.0001
Data Index: 149162 (C4 (Web Text))
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #19