Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3698 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 1.3051. Min Range: -1.3051
Max Act: 1.3051. Min Act: -0.0001
Data Index: 1321707 (C4 (Web Text))
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.3051. Min Range: -1.3051
Max Act: 0.0497. Min Act: -0.0001
Data Index: 34723 (C4 (Web Text))
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.3051. Min Range: -1.3051
Max Act: 0.0437. Min Act: -0.0001
Data Index: 323501 (C4 (Web Text))
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.3051. Min Range: -1.3051
Max Act: 0.0422. Min Act: -0.0001
Data Index: 566794 (C4 (Web Text))
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.3051. Min Range: -1.3051
Max Act: 0.0421. Min Act: -0.0001
Data Index: 477420 (C4 (Web Text))
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.3051. Min Range: -1.3051
Max Act: 0.0403. Min Act: -0.0001
Data Index: 960889 (C4 (Web Text))
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.3051. Min Range: -1.3051
Max Act: 0.0405. Min Act: -0.0001
Data Index: 516999 (C4 (Web Text))
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.3051. Min Range: -1.3051
Max Act: 0.0361. Min Act: -0.0001
Data Index: 688020 (C4 (Web Text))
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.3051. Min Range: -1.3051
Max Act: 0.0349. Min Act: -0.0001
Data Index: 60689 (C4 (Web Text))
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.3051. Min Range: -1.3051
Max Act: 0.0347. Min Act: -0.0001
Data Index: 551490 (C4 (Web Text))
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.3051. Min Range: -1.3051
Max Act: 0.0339. Min Act: -0.0001
Data Index: 57414 (C4 (Web Text))
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.3051. Min Range: -1.3051
Max Act: 0.0352. Min Act: -0.0001
Data Index: 1329521 (C4 (Web Text))
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.3051. Min Range: -1.3051
Max Act: 0.0316. Min Act: -0.0001
Data Index: 549343 (C4 (Web Text))
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.3051. Min Range: -1.3051
Max Act: 0.0315. Min Act: -0.0001
Data Index: 1255208 (C4 (Web Text))
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.3051. Min Range: -1.3051
Max Act: 0.0315. Min Act: -0.0001
Data Index: 949082 (C4 (Web Text))
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.3051. Min Range: -1.3051
Max Act: 0.0315. Min Act: -0.0001
Data Index: 1130276 (C4 (Web Text))
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.3051. Min Range: -1.3051
Max Act: 0.0327. Min Act: -0.0001
Data Index: 193365 (C4 (Web Text))
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.3051. Min Range: -1.3051
Max Act: 0.0302. Min Act: -0.0001
Data Index: 819276 (C4 (Web Text))
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.3051. Min Range: -1.3051
Max Act: 0.0308. Min Act: -0.0001
Data Index: 343289 (C4 (Web Text))
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.3051. Min Range: -1.3051
Max Act: 0.0294. Min Act: -0.0001
Data Index: 47335 (C4 (Web Text))
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #19