Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 642 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 1.9304. Min Range: -1.9304
Max Act: 1.7216. Min Act: -0.0001
Data Index: 551667 (C4 (Web Text))
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.9304. Min Range: -1.9304
Max Act: 1.9304. Min Act: -0.0001
Data Index: 26529 (C4 (Web Text))
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.9304. Min Range: -1.9304
Max Act: 1.8280. Min Act: -0.0001
Data Index: 665449 (C4 (Web Text))
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.9304. Min Range: -1.9304
Max Act: 1.8930. Min Act: -0.0001
Data Index: 163588 (C4 (Web Text))
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.9304. Min Range: -1.9304
Max Act: 1.6075. Min Act: -0.0001
Data Index: 1059588 (C4 (Web Text))
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.9304. Min Range: -1.9304
Max Act: 1.6136. Min Act: -0.0001
Data Index: 767693 (C4 (Web Text))
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.9304. Min Range: -1.9304
Max Act: 1.8404. Min Act: -0.0001
Data Index: 900485 (C4 (Web Text))
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.9304. Min Range: -1.9304
Max Act: 1.7112. Min Act: -0.0001
Data Index: 368736 (C4 (Web Text))
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.9304. Min Range: -1.9304
Max Act: 1.6470. Min Act: -0.0001
Data Index: 305588 (C4 (Web Text))
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.9304. Min Range: -1.9304
Max Act: 1.5977. Min Act: -0.0001
Data Index: 877920 (C4 (Web Text))
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.9304. Min Range: -1.9304
Max Act: 1.6806. Min Act: -0.0001
Data Index: 840350 (C4 (Web Text))
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.9304. Min Range: -1.9304
Max Act: 1.8494. Min Act: -0.0001
Data Index: 1069495 (C4 (Web Text))
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.9304. Min Range: -1.9304
Max Act: 1.5944. Min Act: -0.0001
Data Index: 218055 (C4 (Web Text))
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.9304. Min Range: -1.9304
Max Act: 1.3705. Min Act: -0.0001
Data Index: 265835 (C4 (Web Text))
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.9304. Min Range: -1.9304
Max Act: 1.6562. Min Act: -0.0001
Data Index: 1080057 (C4 (Web Text))
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.9304. Min Range: -1.9304
Max Act: 1.6823. Min Act: -0.0001
Data Index: 632910 (C4 (Web Text))
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.9304. Min Range: -1.9304
Max Act: 1.6256. Min Act: -0.0001
Data Index: 1236747 (C4 (Web Text))
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.9304. Min Range: -1.9304
Max Act: 1.4180. Min Act: -0.0001
Data Index: 549534 (C4 (Web Text))
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.9304. Min Range: -1.9304
Max Act: 1.5791. Min Act: -0.0001
Data Index: 743673 (C4 (Web Text))
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.9304. Min Range: -1.9304
Max Act: 1.7278. Min Act: -0.0001
Data Index: 690164 (C4 (Web Text))
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #19