Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2824 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 1.8202. Min Range: -1.8202
Max Act: 1.8202. Min Act: -0.0001
Data Index: 260457 (C4 (Web Text))
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.8202. Min Range: -1.8202
Max Act: 1.6796. Min Act: -0.0001
Data Index: 536908 (C4 (Web Text))
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.8202. Min Range: -1.8202
Max Act: 1.6903. Min Act: -0.0001
Data Index: 206650 (C4 (Web Text))
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.8202. Min Range: -1.8202
Max Act: 1.6838. Min Act: -0.0001
Data Index: 466187 (C4 (Web Text))
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.8202. Min Range: -1.8202
Max Act: 1.6491. Min Act: -0.0001
Data Index: 1062582 (C4 (Web Text))
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.8202. Min Range: -1.8202
Max Act: 1.6491. Min Act: -0.0001
Data Index: 362998 (C4 (Web Text))
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.8202. Min Range: -1.8202
Max Act: 1.5120. Min Act: -0.0001
Data Index: 926213 (C4 (Web Text))
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.8202. Min Range: -1.8202
Max Act: 1.4696. Min Act: -0.0001
Data Index: 495420 (C4 (Web Text))
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.8202. Min Range: -1.8202
Max Act: 1.6206. Min Act: -0.0001
Data Index: 1272017 (C4 (Web Text))
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.8202. Min Range: -1.8202
Max Act: 1.5303. Min Act: -0.0001
Data Index: 428234 (C4 (Web Text))
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.8202. Min Range: -1.8202
Max Act: 1.4313. Min Act: -0.0001
Data Index: 455741 (C4 (Web Text))
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.8202. Min Range: -1.8202
Max Act: 1.5121. Min Act: -0.0001
Data Index: 216486 (C4 (Web Text))
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.8202. Min Range: -1.8202
Max Act: 1.4956. Min Act: -0.0001
Data Index: 16440 (C4 (Web Text))
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.8202. Min Range: -1.8202
Max Act: 1.5817. Min Act: -0.0001
Data Index: 879561 (C4 (Web Text))
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.8202. Min Range: -1.8202
Max Act: 1.4149. Min Act: -0.0001
Data Index: 166703 (C4 (Web Text))
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.8202. Min Range: -1.8202
Max Act: 1.4671. Min Act: -0.0001
Data Index: 748483 (C4 (Web Text))
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.8202. Min Range: -1.8202
Max Act: 1.4552. Min Act: -0.0001
Data Index: 716966 (C4 (Web Text))
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.8202. Min Range: -1.8202
Max Act: 1.3091. Min Act: -0.0001
Data Index: 21990 (C4 (Web Text))
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.8202. Min Range: -1.8202
Max Act: 1.4643. Min Act: -0.0001
Data Index: 545730 (C4 (Web Text))
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.8202. Min Range: -1.8202
Max Act: 1.2599. Min Act: -0.0001
Data Index: 999627 (C4 (Web Text))
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #19