Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 5 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 1.3081. Min Range: -1.3081
Max Act: 1.1946. Min Act: -0.0001
Data Index: 426134 (C4 (Web Text))
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.3081. Min Range: -1.3081
Max Act: 1.3081. Min Act: -0.0001
Data Index: 649802 (C4 (Web Text))
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.3081. Min Range: -1.3081
Max Act: 1.2203. Min Act: -0.0001
Data Index: 450573 (C4 (Web Text))
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.3081. Min Range: -1.3081
Max Act: 1.2445. Min Act: -0.0001
Data Index: 1074060 (C4 (Web Text))
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.3081. Min Range: -1.3081
Max Act: 1.0452. Min Act: -0.0001
Data Index: 1119600 (C4 (Web Text))
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.3081. Min Range: -1.3081
Max Act: 0.9934. Min Act: -0.0001
Data Index: 908579 (C4 (Web Text))
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.3081. Min Range: -1.3081
Max Act: 0.9694. Min Act: -0.0001
Data Index: 602225 (C4 (Web Text))
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.3081. Min Range: -1.3081
Max Act: 1.0053. Min Act: -0.0001
Data Index: 879290 (C4 (Web Text))
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.3081. Min Range: -1.3081
Max Act: 1.0477. Min Act: -0.0001
Data Index: 1034387 (C4 (Web Text))
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.3081. Min Range: -1.3081
Max Act: 0.9767. Min Act: -0.0001
Data Index: 577217 (C4 (Web Text))
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.3081. Min Range: -1.3081
Max Act: 0.9308. Min Act: -0.0001
Data Index: 1094131 (C4 (Web Text))
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.3081. Min Range: -1.3081
Max Act: 0.9809. Min Act: -0.0001
Data Index: 109265 (C4 (Web Text))
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.3081. Min Range: -1.3081
Max Act: 0.9198. Min Act: -0.0001
Data Index: 557751 (C4 (Web Text))
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.3081. Min Range: -1.3081
Max Act: 0.9893. Min Act: -0.0001
Data Index: 71866 (C4 (Web Text))
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.3081. Min Range: -1.3081
Max Act: 0.9058. Min Act: -0.0001
Data Index: 493990 (C4 (Web Text))
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.3081. Min Range: -1.3081
Max Act: 0.9256. Min Act: -0.0001
Data Index: 411915 (C4 (Web Text))
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.3081. Min Range: -1.3081
Max Act: 0.9015. Min Act: -0.0001
Data Index: 922409 (C4 (Web Text))
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.3081. Min Range: -1.3081
Max Act: 0.8589. Min Act: -0.0001
Data Index: 372641 (C4 (Web Text))
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.3081. Min Range: -1.3081
Max Act: 0.8918. Min Act: -0.0001
Data Index: 86782 (C4 (Web Text))
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.3081. Min Range: -1.3081
Max Act: 0.7757. Min Act: -0.0001
Data Index: 1045080 (C4 (Web Text))
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #19