Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 70 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 1.8116. Min Range: -1.8116
Max Act: 1.8116. Min Act: -0.0001
Data Index: 758270 (C4 (Web Text))
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.8116. Min Range: -1.8116
Max Act: 1.4104. Min Act: -0.0001
Data Index: 204934 (C4 (Web Text))
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.8116. Min Range: -1.8116
Max Act: 1.3930. Min Act: -0.0001
Data Index: 1285858 (C4 (Web Text))
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.8116. Min Range: -1.8116
Max Act: 1.3468. Min Act: -0.0001
Data Index: 544398 (C4 (Web Text))
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.8116. Min Range: -1.8116
Max Act: 1.2417. Min Act: -0.0001
Data Index: 156030 (C4 (Web Text))
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.8116. Min Range: -1.8116
Max Act: 1.2479. Min Act: -0.0001
Data Index: 445201 (C4 (Web Text))
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.8116. Min Range: -1.8116
Max Act: 1.2838. Min Act: -0.0001
Data Index: 1169896 (C4 (Web Text))
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.8116. Min Range: -1.8116
Max Act: 1.2476. Min Act: -0.0001
Data Index: 182240 (C4 (Web Text))
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.8116. Min Range: -1.8116
Max Act: 1.2031. Min Act: -0.0001
Data Index: 501670 (C4 (Web Text))
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.8116. Min Range: -1.8116
Max Act: 1.2405. Min Act: -0.0001
Data Index: 659916 (C4 (Web Text))
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.8116. Min Range: -1.8116
Max Act: 1.1799. Min Act: -0.0001
Data Index: 766697 (C4 (Web Text))
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.8116. Min Range: -1.8116
Max Act: 1.2412. Min Act: -0.0001
Data Index: 4044 (C4 (Web Text))
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.8116. Min Range: -1.8116
Max Act: 1.2344. Min Act: -0.0001
Data Index: 1017176 (C4 (Web Text))
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.8116. Min Range: -1.8116
Max Act: 1.1448. Min Act: -0.0001
Data Index: 720865 (C4 (Web Text))
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.8116. Min Range: -1.8116
Max Act: 1.1296. Min Act: -0.0001
Data Index: 465530 (C4 (Web Text))
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.8116. Min Range: -1.8116
Max Act: 1.0776. Min Act: -0.0001
Data Index: 969376 (C4 (Web Text))
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.8116. Min Range: -1.8116
Max Act: 1.1287. Min Act: -0.0001
Data Index: 365200 (C4 (Web Text))
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.8116. Min Range: -1.8116
Max Act: 1.2298. Min Act: -0.0001
Data Index: 404939 (C4 (Web Text))
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.8116. Min Range: -1.8116
Max Act: 1.1267. Min Act: -0.0001
Data Index: 379091 (C4 (Web Text))
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.8116. Min Range: -1.8116
Max Act: 1.1785. Min Act: -0.0001
Data Index: 1206248 (C4 (Web Text))
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #19