Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3712 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 1.1365. Min Range: -1.1365
Max Act: 1.0795. Min Act: -0.0001
Data Index: 185197 (C4 (Web Text))
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.1365. Min Range: -1.1365
Max Act: 1.1365. Min Act: -0.0001
Data Index: 7201 (C4 (Web Text))
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.1365. Min Range: -1.1365
Max Act: 1.1360. Min Act: -0.0001
Data Index: 740685 (C4 (Web Text))
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.1365. Min Range: -1.1365
Max Act: 1.1164. Min Act: -0.0001
Data Index: 570312 (C4 (Web Text))
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.1365. Min Range: -1.1365
Max Act: 1.0473. Min Act: -0.0001
Data Index: 696898 (C4 (Web Text))
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.1365. Min Range: -1.1365
Max Act: 1.0460. Min Act: -0.0001
Data Index: 506713 (C4 (Web Text))
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.1365. Min Range: -1.1365
Max Act: 0.9583. Min Act: -0.0001
Data Index: 727120 (C4 (Web Text))
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.1365. Min Range: -1.1365
Max Act: 0.9523. Min Act: -0.0001
Data Index: 54939 (C4 (Web Text))
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.1365. Min Range: -1.1365
Max Act: 0.9849. Min Act: -0.0001
Data Index: 346565 (C4 (Web Text))
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.1365. Min Range: -1.1365
Max Act: 0.9560. Min Act: -0.0001
Data Index: 1290740 (C4 (Web Text))
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.1365. Min Range: -1.1365
Max Act: 0.9413. Min Act: -0.0001
Data Index: 654991 (C4 (Web Text))
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.1365. Min Range: -1.1365
Max Act: 0.9240. Min Act: -0.0001
Data Index: 46518 (C4 (Web Text))
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.1365. Min Range: -1.1365
Max Act: 0.9223. Min Act: -0.0001
Data Index: 559479 (C4 (Web Text))
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.1365. Min Range: -1.1365
Max Act: 0.9586. Min Act: -0.0001
Data Index: 815455 (C4 (Web Text))
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.1365. Min Range: -1.1365
Max Act: 0.8799. Min Act: -0.0001
Data Index: 57851 (C4 (Web Text))
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.1365. Min Range: -1.1365
Max Act: 0.9347. Min Act: -0.0001
Data Index: 73697 (C4 (Web Text))
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.1365. Min Range: -1.1365
Max Act: 0.8348. Min Act: -0.0001
Data Index: 274014 (C4 (Web Text))
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.1365. Min Range: -1.1365
Max Act: 0.9150. Min Act: -0.0001
Data Index: 574840 (C4 (Web Text))
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.1365. Min Range: -1.1365
Max Act: 0.8897. Min Act: -0.0001
Data Index: 296030 (C4 (Web Text))
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.1365. Min Range: -1.1365
Max Act: 0.8120. Min Act: -0.0001
Data Index: 247597 (C4 (Web Text))
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #19