Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 10 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 1.8364. Min Range: -1.8364
Max Act: 1.8364. Min Act: -0.0001
Data Index: 582154 (C4 (Web Text))
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.8364. Min Range: -1.8364
Max Act: 1.6876. Min Act: -0.0001
Data Index: 175038 (C4 (Web Text))
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.8364. Min Range: -1.8364
Max Act: 1.6204. Min Act: -0.0001
Data Index: 1290175 (C4 (Web Text))
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.8364. Min Range: -1.8364
Max Act: 1.5554. Min Act: -0.0001
Data Index: 1108145 (C4 (Web Text))
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.8364. Min Range: -1.8364
Max Act: 1.6109. Min Act: -0.0001
Data Index: 978897 (C4 (Web Text))
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.8364. Min Range: -1.8364
Max Act: 1.5567. Min Act: -0.0001
Data Index: 838004 (C4 (Web Text))
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.8364. Min Range: -1.8364
Max Act: 1.4040. Min Act: -0.0001
Data Index: 624347 (C4 (Web Text))
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.8364. Min Range: -1.8364
Max Act: 1.5374. Min Act: -0.0001
Data Index: 1230588 (C4 (Web Text))
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.8364. Min Range: -1.8364
Max Act: 1.4365. Min Act: -0.0001
Data Index: 38580 (C4 (Web Text))
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.8364. Min Range: -1.8364
Max Act: 1.5281. Min Act: -0.0001
Data Index: 529120 (C4 (Web Text))
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.8364. Min Range: -1.8364
Max Act: 1.4094. Min Act: -0.0001
Data Index: 623474 (C4 (Web Text))
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.8364. Min Range: -1.8364
Max Act: 1.3690. Min Act: -0.0001
Data Index: 964333 (C4 (Web Text))
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.8364. Min Range: -1.8364
Max Act: 1.3811. Min Act: -0.0001
Data Index: 127101 (C4 (Web Text))
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.8364. Min Range: -1.8364
Max Act: 1.3154. Min Act: -0.0001
Data Index: 66878 (C4 (Web Text))
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.8364. Min Range: -1.8364
Max Act: 1.2708. Min Act: -0.0001
Data Index: 796901 (C4 (Web Text))
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.8364. Min Range: -1.8364
Max Act: 1.2186. Min Act: -0.0001
Data Index: 999727 (C4 (Web Text))
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.8364. Min Range: -1.8364
Max Act: 1.3314. Min Act: -0.0001
Data Index: 563675 (C4 (Web Text))
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.8364. Min Range: -1.8364
Max Act: 1.2478. Min Act: -0.0001
Data Index: 642981 (C4 (Web Text))
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.8364. Min Range: -1.8364
Max Act: 1.2405. Min Act: -0.0001
Data Index: 414819 (C4 (Web Text))
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.8364. Min Range: -1.8364
Max Act: 1.2719. Min Act: -0.0001
Data Index: 435891 (C4 (Web Text))
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #19