Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2279 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 2.3423. Min Range: -2.3423
Max Act: 2.2544. Min Act: -0.0001
Data Index: 1141337 (C4 (Web Text))
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.3423. Min Range: -2.3423
Max Act: 2.2219. Min Act: -0.0001
Data Index: 129166 (C4 (Web Text))
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.3423. Min Range: -2.3423
Max Act: 2.3423. Min Act: -0.0001
Data Index: 1311443 (C4 (Web Text))
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.3423. Min Range: -2.3423
Max Act: 2.3142. Min Act: -0.0001
Data Index: 544437 (C4 (Web Text))
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.3423. Min Range: -2.3423
Max Act: 2.1805. Min Act: -0.0001
Data Index: 611269 (C4 (Web Text))
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.3423. Min Range: -2.3423
Max Act: 2.1008. Min Act: -0.0001
Data Index: 933035 (C4 (Web Text))
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.3423. Min Range: -2.3423
Max Act: 2.0759. Min Act: -0.0001
Data Index: 989003 (C4 (Web Text))
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.3423. Min Range: -2.3423
Max Act: 2.0867. Min Act: -0.0001
Data Index: 491991 (C4 (Web Text))
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.3423. Min Range: -2.3423
Max Act: 1.9207. Min Act: -0.0001
Data Index: 1286095 (C4 (Web Text))
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.3423. Min Range: -2.3423
Max Act: 1.9083. Min Act: -0.0001
Data Index: 1306280 (C4 (Web Text))
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.3423. Min Range: -2.3423
Max Act: 1.9072. Min Act: -0.0001
Data Index: 1261810 (C4 (Web Text))
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.3423. Min Range: -2.3423
Max Act: 1.9757. Min Act: -0.0001
Data Index: 1031505 (C4 (Web Text))
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.3423. Min Range: -2.3423
Max Act: 1.8664. Min Act: -0.0001
Data Index: 378191 (C4 (Web Text))
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.3423. Min Range: -2.3423
Max Act: 1.8713. Min Act: -0.0001
Data Index: 1642247 (Python Code)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.3423. Min Range: -2.3423
Max Act: 1.8166. Min Act: -0.0001
Data Index: 856259 (C4 (Web Text))
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.3423. Min Range: -2.3423
Max Act: 1.8623. Min Act: -0.0001
Data Index: 769446 (C4 (Web Text))
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.3423. Min Range: -2.3423
Max Act: 1.8452. Min Act: -0.0001
Data Index: 1121208 (C4 (Web Text))
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.3423. Min Range: -2.3423
Max Act: 1.7778. Min Act: -0.0001
Data Index: 925720 (C4 (Web Text))
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.3423. Min Range: -2.3423
Max Act: 1.7096. Min Act: -0.0001
Data Index: 469264 (C4 (Web Text))
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.3423. Min Range: -2.3423
Max Act: 1.8072. Min Act: -0.0001
Data Index: 1411129 (Python Code)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #19