Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 967 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 3.5459. Min Range: -3.5459
Max Act: 3.5459. Min Act: -0.0001
Data Index: 924015 (C4 (Web Text))
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5459. Min Range: -3.5459
Max Act: 2.7735. Min Act: -0.0001
Data Index: 970637 (C4 (Web Text))
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5459. Min Range: -3.5459
Max Act: 3.0530. Min Act: -0.0001
Data Index: 974839 (C4 (Web Text))
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5459. Min Range: -3.5459
Max Act: 2.7732. Min Act: -0.0001
Data Index: 946269 (C4 (Web Text))
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5459. Min Range: -3.5459
Max Act: 2.7872. Min Act: -0.0001
Data Index: 1039999 (C4 (Web Text))
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5459. Min Range: -3.5459
Max Act: 2.8501. Min Act: -0.0001
Data Index: 383224 (C4 (Web Text))
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5459. Min Range: -3.5459
Max Act: 2.8710. Min Act: -0.0001
Data Index: 922351 (C4 (Web Text))
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5459. Min Range: -3.5459
Max Act: 2.7277. Min Act: -0.0001
Data Index: 1239198 (C4 (Web Text))
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5459. Min Range: -3.5459
Max Act: 2.1942. Min Act: -0.0001
Data Index: 551444 (C4 (Web Text))
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5459. Min Range: -3.5459
Max Act: 2.5358. Min Act: -0.0001
Data Index: 1110649 (C4 (Web Text))
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5459. Min Range: -3.5459
Max Act: 2.4027. Min Act: -0.0001
Data Index: 908064 (C4 (Web Text))
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5459. Min Range: -3.5459
Max Act: 2.4631. Min Act: -0.0001
Data Index: 223305 (C4 (Web Text))
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5459. Min Range: -3.5459
Max Act: 2.3856. Min Act: -0.0001
Data Index: 693085 (C4 (Web Text))
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5459. Min Range: -3.5459
Max Act: 2.1500. Min Act: -0.0001
Data Index: 812559 (C4 (Web Text))
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5459. Min Range: -3.5459
Max Act: 2.2670. Min Act: -0.0001
Data Index: 784998 (C4 (Web Text))
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5459. Min Range: -3.5459
Max Act: 2.3697. Min Act: -0.0001
Data Index: 1324399 (C4 (Web Text))
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5459. Min Range: -3.5459
Max Act: 1.9647. Min Act: -0.0001
Data Index: 383183 (C4 (Web Text))
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5459. Min Range: -3.5459
Max Act: 1.8910. Min Act: -0.0001
Data Index: 1064294 (C4 (Web Text))
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5459. Min Range: -3.5459
Max Act: 2.0498. Min Act: -0.0001
Data Index: 387941 (C4 (Web Text))
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5459. Min Range: -3.5459
Max Act: 2.2780. Min Act: -0.0001
Data Index: 1073520 (C4 (Web Text))
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #19