Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2789 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 4.4099. Min Range: -4.4099
Max Act: 4.2976. Min Act: -0.0001
Data Index: 1319117 (C4 (Web Text))
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4099. Min Range: -4.4099
Max Act: 4.4099. Min Act: -0.0001
Data Index: 1268890 (C4 (Web Text))
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4099. Min Range: -4.4099
Max Act: 3.5356. Min Act: -0.0001
Data Index: 664043 (C4 (Web Text))
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4099. Min Range: -4.4099
Max Act: 3.4954. Min Act: -0.0001
Data Index: 1104235 (C4 (Web Text))
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4099. Min Range: -4.4099
Max Act: 3.7412. Min Act: -0.0001
Data Index: 308396 (C4 (Web Text))
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4099. Min Range: -4.4099
Max Act: 3.8828. Min Act: -0.0001
Data Index: 1037243 (C4 (Web Text))
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4099. Min Range: -4.4099
Max Act: 3.4892. Min Act: -0.0001
Data Index: 885203 (C4 (Web Text))
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4099. Min Range: -4.4099
Max Act: 3.3583. Min Act: -0.0001
Data Index: 1345185 (C4 (Web Text))
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4099. Min Range: -4.4099
Max Act: 3.1808. Min Act: -0.0001
Data Index: 937406 (C4 (Web Text))
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4099. Min Range: -4.4099
Max Act: 3.3263. Min Act: -0.0001
Data Index: 950587 (C4 (Web Text))
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4099. Min Range: -4.4099
Max Act: 3.4226. Min Act: -0.0001
Data Index: 393969 (C4 (Web Text))
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4099. Min Range: -4.4099
Max Act: 3.4675. Min Act: -0.0001
Data Index: 151782 (C4 (Web Text))
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4099. Min Range: -4.4099
Max Act: 3.1124. Min Act: -0.0001
Data Index: 887103 (C4 (Web Text))
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4099. Min Range: -4.4099
Max Act: 3.2459. Min Act: -0.0001
Data Index: 746822 (C4 (Web Text))
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4099. Min Range: -4.4099
Max Act: 3.2421. Min Act: -0.0001
Data Index: 1026389 (C4 (Web Text))
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4099. Min Range: -4.4099
Max Act: 3.3815. Min Act: -0.0001
Data Index: 601094 (C4 (Web Text))
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4099. Min Range: -4.4099
Max Act: 2.9731. Min Act: -0.0001
Data Index: 364969 (C4 (Web Text))
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4099. Min Range: -4.4099
Max Act: 3.2046. Min Act: -0.0001
Data Index: 739333 (C4 (Web Text))
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4099. Min Range: -4.4099
Max Act: 3.1762. Min Act: -0.0001
Data Index: 1249684 (C4 (Web Text))
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4099. Min Range: -4.4099
Max Act: 3.0257. Min Act: -0.0001
Data Index: 330223 (C4 (Web Text))
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #19