Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 4591 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 0.5459. Min Range: -0.5459
Max Act: 0.5457. Min Act: -0.0001
Data Index: 962808 (C4 (Web Text))
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.5459. Min Range: -0.5459
Max Act: 0.4591. Min Act: -0.0001
Data Index: 1083402 (C4 (Web Text))
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.5459. Min Range: -0.5459
Max Act: 0.4881. Min Act: -0.0001
Data Index: 952502 (C4 (Web Text))
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.5459. Min Range: -0.5459
Max Act: 0.4850. Min Act: -0.0001
Data Index: 329801 (C4 (Web Text))
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.5459. Min Range: -0.5459
Max Act: 0.4643. Min Act: -0.0001
Data Index: 610177 (C4 (Web Text))
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.5459. Min Range: -0.5459
Max Act: 0.4607. Min Act: -0.0001
Data Index: 451512 (C4 (Web Text))
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.5459. Min Range: -0.5459
Max Act: 0.4692. Min Act: -0.0001
Data Index: 255982 (C4 (Web Text))
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.5459. Min Range: -0.5459
Max Act: 0.4512. Min Act: -0.0001
Data Index: 1084710 (C4 (Web Text))
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.5459. Min Range: -0.5459
Max Act: 0.4415. Min Act: -0.0001
Data Index: 700246 (C4 (Web Text))
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.5459. Min Range: -0.5459
Max Act: 0.4987. Min Act: -0.0001
Data Index: 960101 (C4 (Web Text))
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.5459. Min Range: -0.5459
Max Act: 0.4022. Min Act: -0.0001
Data Index: 528478 (C4 (Web Text))
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.5459. Min Range: -0.5459
Max Act: 0.4271. Min Act: -0.0001
Data Index: 417956 (C4 (Web Text))
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.5459. Min Range: -0.5459
Max Act: 0.4517. Min Act: -0.0001
Data Index: 1034303 (C4 (Web Text))
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.5459. Min Range: -0.5459
Max Act: 0.4505. Min Act: -0.0001
Data Index: 452122 (C4 (Web Text))
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.5459. Min Range: -0.5459
Max Act: 0.3701. Min Act: -0.0001
Data Index: 1221426 (C4 (Web Text))
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.5459. Min Range: -0.5459
Max Act: 0.4487. Min Act: -0.0001
Data Index: 296515 (C4 (Web Text))
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.5459. Min Range: -0.5459
Max Act: 0.4381. Min Act: -0.0001
Data Index: 1233239 (C4 (Web Text))
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.5459. Min Range: -0.5459
Max Act: 0.3820. Min Act: -0.0001
Data Index: 1214082 (C4 (Web Text))
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.5459. Min Range: -0.5459
Max Act: 0.5459. Min Act: -0.0001
Data Index: 1272204 (C4 (Web Text))
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.5459. Min Range: -0.5459
Max Act: 0.4056. Min Act: -0.0001
Data Index: 136808 (C4 (Web Text))
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #19