Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3496 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 3.2466. Min Range: -3.2466
Max Act: 3.2466. Min Act: -0.0001
Data Index: 375153 (C4 (Web Text))
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2466. Min Range: -3.2466
Max Act: 2.8049. Min Act: -0.0001
Data Index: 215278 (C4 (Web Text))
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2466. Min Range: -3.2466
Max Act: 2.8653. Min Act: -0.0001
Data Index: 226539 (C4 (Web Text))
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2466. Min Range: -3.2466
Max Act: 2.9118. Min Act: -0.0001
Data Index: 420743 (C4 (Web Text))
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2466. Min Range: -3.2466
Max Act: 2.4650. Min Act: -0.0001
Data Index: 57157 (C4 (Web Text))
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2466. Min Range: -3.2466
Max Act: 2.0953. Min Act: -0.0001
Data Index: 802057 (C4 (Web Text))
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2466. Min Range: -3.2466
Max Act: 2.2919. Min Act: -0.0001
Data Index: 1158169 (C4 (Web Text))
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2466. Min Range: -3.2466
Max Act: 2.0635. Min Act: -0.0001
Data Index: 426427 (C4 (Web Text))
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2466. Min Range: -3.2466
Max Act: 2.2233. Min Act: -0.0001
Data Index: 777092 (C4 (Web Text))
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2466. Min Range: -3.2466
Max Act: 2.1028. Min Act: -0.0001
Data Index: 541458 (C4 (Web Text))
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2466. Min Range: -3.2466
Max Act: 2.1028. Min Act: -0.0001
Data Index: 166116 (C4 (Web Text))
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2466. Min Range: -3.2466
Max Act: 2.0687. Min Act: -0.0001
Data Index: 242518 (C4 (Web Text))
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2466. Min Range: -3.2466
Max Act: 2.0578. Min Act: -0.0001
Data Index: 941522 (C4 (Web Text))
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2466. Min Range: -3.2466
Max Act: 2.0487. Min Act: -0.0001
Data Index: 1164555 (C4 (Web Text))
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2466. Min Range: -3.2466
Max Act: 1.9709. Min Act: -0.0001
Data Index: 179442 (C4 (Web Text))
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2466. Min Range: -3.2466
Max Act: 2.1891. Min Act: -0.0001
Data Index: 1353567 (C4 (Web Text))
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2466. Min Range: -3.2466
Max Act: 1.9543. Min Act: -0.0001
Data Index: 235697 (C4 (Web Text))
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2466. Min Range: -3.2466
Max Act: 2.0719. Min Act: -0.0001
Data Index: 612480 (C4 (Web Text))
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2466. Min Range: -3.2466
Max Act: 1.7362. Min Act: -0.0001
Data Index: 856783 (C4 (Web Text))
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2466. Min Range: -3.2466
Max Act: 2.0582. Min Act: -0.0001
Data Index: 565072 (C4 (Web Text))
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #19