Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1137 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 2.8267. Min Range: -2.8267
Max Act: 2.8267. Min Act: -0.0001
Data Index: 257943 (C4 (Web Text))
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8267. Min Range: -2.8267
Max Act: 2.7203. Min Act: -0.0001
Data Index: 447001 (C4 (Web Text))
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8267. Min Range: -2.8267
Max Act: 2.5098. Min Act: -0.0001
Data Index: 501407 (C4 (Web Text))
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8267. Min Range: -2.8267
Max Act: 2.7620. Min Act: -0.0001
Data Index: 747858 (C4 (Web Text))
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8267. Min Range: -2.8267
Max Act: 2.4906. Min Act: -0.0001
Data Index: 295397 (C4 (Web Text))
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8267. Min Range: -2.8267
Max Act: 2.6094. Min Act: -0.0001
Data Index: 966152 (C4 (Web Text))
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8267. Min Range: -2.8267
Max Act: 2.3349. Min Act: -0.0001
Data Index: 672496 (C4 (Web Text))
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8267. Min Range: -2.8267
Max Act: 2.6675. Min Act: -0.0001
Data Index: 1135430 (C4 (Web Text))
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8267. Min Range: -2.8267
Max Act: 2.5534. Min Act: -0.0001
Data Index: 910337 (C4 (Web Text))
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8267. Min Range: -2.8267
Max Act: 2.7942. Min Act: -0.0001
Data Index: 432619 (C4 (Web Text))
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8267. Min Range: -2.8267
Max Act: 2.4191. Min Act: -0.0001
Data Index: 1234040 (C4 (Web Text))
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8267. Min Range: -2.8267
Max Act: 2.3882. Min Act: -0.0001
Data Index: 1077105 (C4 (Web Text))
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8267. Min Range: -2.8267
Max Act: 2.6181. Min Act: -0.0001
Data Index: 1199705 (C4 (Web Text))
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8267. Min Range: -2.8267
Max Act: 2.3446. Min Act: -0.0001
Data Index: 690096 (C4 (Web Text))
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8267. Min Range: -2.8267
Max Act: 2.2393. Min Act: -0.0001
Data Index: 371763 (C4 (Web Text))
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8267. Min Range: -2.8267
Max Act: 2.4352. Min Act: -0.0001
Data Index: 534937 (C4 (Web Text))
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8267. Min Range: -2.8267
Max Act: 2.3129. Min Act: -0.0001
Data Index: 95197 (C4 (Web Text))
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8267. Min Range: -2.8267
Max Act: 2.5484. Min Act: -0.0001
Data Index: 1036883 (C4 (Web Text))
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8267. Min Range: -2.8267
Max Act: 2.2676. Min Act: -0.0001
Data Index: 918112 (C4 (Web Text))
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8267. Min Range: -2.8267
Max Act: 2.5204. Min Act: -0.0001
Data Index: 336159 (C4 (Web Text))
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #19