Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: The Pile
Neuron 197 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')
Text #0
Max Range: 0.4416. Min Range: -0.4416
Max Act: 0.4416. Min Act: -0.0001
Data Index: 347551 (The Pile)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.4416. Min Range: -0.4416
Max Act: 0.3817. Min Act: -0.0001
Data Index: 197722 (The Pile)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.4416. Min Range: -0.4416
Max Act: 0.4121. Min Act: -0.0001
Data Index: 499681 (The Pile)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.4416. Min Range: -0.4416
Max Act: 0.3263. Min Act: -0.0001
Data Index: 1083094 (The Pile)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.4416. Min Range: -0.4416
Max Act: 0.3101. Min Act: -0.0001
Data Index: 942584 (The Pile)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.4416. Min Range: -0.4416
Max Act: 0.3022. Min Act: -0.0001
Data Index: 1007455 (The Pile)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.4416. Min Range: -0.4416
Max Act: 0.1825. Min Act: -0.0001
Data Index: 705586 (The Pile)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.4416. Min Range: -0.4416
Max Act: 0.3035. Min Act: -0.0001
Data Index: 858340 (The Pile)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.4416. Min Range: -0.4416
Max Act: 0.2879. Min Act: -0.0001
Data Index: 715754 (The Pile)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.4416. Min Range: -0.4416
Max Act: 0.3281. Min Act: -0.0001
Data Index: 442399 (The Pile)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.4416. Min Range: -0.4416
Max Act: 0.2701. Min Act: -0.0001
Data Index: 386829 (The Pile)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.4416. Min Range: -0.4416
Max Act: 0.2291. Min Act: -0.0001
Data Index: 1983704 (The Pile)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.4416. Min Range: -0.4416
Max Act: 0.2390. Min Act: -0.0001
Data Index: 721697 (The Pile)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.4416. Min Range: -0.4416
Max Act: 0.2352. Min Act: -0.0001
Data Index: 180811 (The Pile)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.4416. Min Range: -0.4416
Max Act: 0.2775. Min Act: -0.0001
Data Index: 414984 (The Pile)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.4416. Min Range: -0.4416
Max Act: 0.2354. Min Act: -0.0001
Data Index: 492944 (The Pile)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.4416. Min Range: -0.4416
Max Act: 0.2425. Min Act: -0.0001
Data Index: 1264360 (The Pile)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.4416. Min Range: -0.4416
Max Act: 0.3094. Min Act: -0.0001
Data Index: 860798 (The Pile)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.4416. Min Range: -0.4416
Max Act: 0.3252. Min Act: -0.0001
Data Index: 790412 (The Pile)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.4416. Min Range: -0.4416
Max Act: 0.1990. Min Act: -0.0001
Data Index: 167319 (The Pile)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #19