Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1841 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 1.8304. Min Range: -1.8304
Max Act: 1.8304. Min Act: -0.0001
Data Index: 1029239 (C4 (Web Text))
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.8304. Min Range: -1.8304
Max Act: 1.7704. Min Act: -0.0001
Data Index: 129026 (C4 (Web Text))
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.8304. Min Range: -1.8304
Max Act: 1.5899. Min Act: -0.0001
Data Index: 665946 (C4 (Web Text))
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.8304. Min Range: -1.8304
Max Act: 1.5850. Min Act: -0.0001
Data Index: 1257925 (C4 (Web Text))
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.8304. Min Range: -1.8304
Max Act: 1.6437. Min Act: -0.0001
Data Index: 1094633 (C4 (Web Text))
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.8304. Min Range: -1.8304
Max Act: 1.5234. Min Act: -0.0001
Data Index: 615130 (C4 (Web Text))
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.8304. Min Range: -1.8304
Max Act: 1.5800. Min Act: -0.0001
Data Index: 1064417 (C4 (Web Text))
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.8304. Min Range: -1.8304
Max Act: 1.5489. Min Act: -0.0001
Data Index: 276642 (C4 (Web Text))
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.8304. Min Range: -1.8304
Max Act: 1.4059. Min Act: -0.0001
Data Index: 781533 (C4 (Web Text))
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.8304. Min Range: -1.8304
Max Act: 1.2452. Min Act: -0.0001
Data Index: 1528904 (Python Code)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.8304. Min Range: -1.8304
Max Act: 1.2733. Min Act: -0.0001
Data Index: 84639 (C4 (Web Text))
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.8304. Min Range: -1.8304
Max Act: 1.3337. Min Act: -0.0001
Data Index: 671827 (C4 (Web Text))
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.8304. Min Range: -1.8304
Max Act: 1.3275. Min Act: -0.0001
Data Index: 979769 (C4 (Web Text))
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.8304. Min Range: -1.8304
Max Act: 1.3222. Min Act: -0.0001
Data Index: 1476864 (Python Code)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.8304. Min Range: -1.8304
Max Act: 1.2456. Min Act: -0.0001
Data Index: 620004 (C4 (Web Text))
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.8304. Min Range: -1.8304
Max Act: 1.3155. Min Act: -0.0001
Data Index: 137548 (C4 (Web Text))
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.8304. Min Range: -1.8304
Max Act: 1.3723. Min Act: -0.0001
Data Index: 550647 (C4 (Web Text))
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.8304. Min Range: -1.8304
Max Act: 1.2970. Min Act: -0.0001
Data Index: 1299841 (C4 (Web Text))
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.8304. Min Range: -1.8304
Max Act: 1.2305. Min Act: -0.0001
Data Index: 1103109 (C4 (Web Text))
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.8304. Min Range: -1.8304
Max Act: 1.2817. Min Act: -0.0001
Data Index: 527807 (C4 (Web Text))
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #19