Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 70 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 2.8151. Min Range: -2.8151
Max Act: 2.8151. Min Act: -0.0001
Data Index: 262024 (C4 (Web Text))
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8151. Min Range: -2.8151
Max Act: 2.6352. Min Act: -0.0001
Data Index: 708117 (C4 (Web Text))
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8151. Min Range: -2.8151
Max Act: 2.4045. Min Act: -0.0000
Data Index: 432602 (C4 (Web Text))
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8151. Min Range: -2.8151
Max Act: 2.3427. Min Act: -0.0001
Data Index: 1355432 (C4 (Web Text))
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8151. Min Range: -2.8151
Max Act: 2.3308. Min Act: -0.0001
Data Index: 1576432 (Python Code)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8151. Min Range: -2.8151
Max Act: 2.2658. Min Act: -0.0001
Data Index: 1283209 (C4 (Web Text))
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8151. Min Range: -2.8151
Max Act: 2.2890. Min Act: -0.0001
Data Index: 900503 (C4 (Web Text))
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8151. Min Range: -2.8151
Max Act: 2.3688. Min Act: -0.0000
Data Index: 101100 (C4 (Web Text))
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8151. Min Range: -2.8151
Max Act: 2.3628. Min Act: -0.0001
Data Index: 691539 (C4 (Web Text))
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8151. Min Range: -2.8151
Max Act: 2.3062. Min Act: -0.0001
Data Index: 963457 (C4 (Web Text))
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8151. Min Range: -2.8151
Max Act: 2.1685. Min Act: -0.0001
Data Index: 1558244 (Python Code)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8151. Min Range: -2.8151
Max Act: 2.1525. Min Act: -0.0001
Data Index: 1132929 (C4 (Web Text))
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8151. Min Range: -2.8151
Max Act: 2.1663. Min Act: -0.0000
Data Index: 1200036 (C4 (Web Text))
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8151. Min Range: -2.8151
Max Act: 2.2639. Min Act: -0.0000
Data Index: 519885 (C4 (Web Text))
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8151. Min Range: -2.8151
Max Act: 2.3760. Min Act: -0.0001
Data Index: 1173003 (C4 (Web Text))
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8151. Min Range: -2.8151
Max Act: 2.3795. Min Act: -0.0000
Data Index: 1509174 (Python Code)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8151. Min Range: -2.8151
Max Act: 2.2264. Min Act: -0.0001
Data Index: 1099763 (C4 (Web Text))
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8151. Min Range: -2.8151
Max Act: 2.3294. Min Act: -0.0000
Data Index: 543089 (C4 (Web Text))
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8151. Min Range: -2.8151
Max Act: 2.2734. Min Act: -0.0000
Data Index: 31520 (C4 (Web Text))
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8151. Min Range: -2.8151
Max Act: 2.0484. Min Act: -0.0001
Data Index: 1648443 (Python Code)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #19