Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3062 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 4.2275. Min Range: -4.2275
Max Act: 4.0759. Min Act: -0.0001
Data Index: 258934 (C4 (Web Text))
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2275. Min Range: -4.2275
Max Act: 3.8220. Min Act: -0.0001
Data Index: 1094340 (C4 (Web Text))
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2275. Min Range: -4.2275
Max Act: 3.6683. Min Act: -0.0001
Data Index: 30632 (C4 (Web Text))
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2275. Min Range: -4.2275
Max Act: 3.8011. Min Act: -0.0001
Data Index: 847312 (C4 (Web Text))
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2275. Min Range: -4.2275
Max Act: 3.7560. Min Act: -0.0001
Data Index: 474532 (C4 (Web Text))
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2275. Min Range: -4.2275
Max Act: 4.2275. Min Act: -0.0001
Data Index: 1460027 (Python Code)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2275. Min Range: -4.2275
Max Act: 3.3960. Min Act: -0.0001
Data Index: 941458 (C4 (Web Text))
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2275. Min Range: -4.2275
Max Act: 3.8710. Min Act: -0.0001
Data Index: 155836 (C4 (Web Text))
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2275. Min Range: -4.2275
Max Act: 3.3851. Min Act: -0.0001
Data Index: 873123 (C4 (Web Text))
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2275. Min Range: -4.2275
Max Act: 3.0597. Min Act: -0.0001
Data Index: 1329766 (C4 (Web Text))
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2275. Min Range: -4.2275
Max Act: 3.4705. Min Act: -0.0001
Data Index: 1519017 (Python Code)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2275. Min Range: -4.2275
Max Act: 3.0101. Min Act: -0.0001
Data Index: 1393209 (Python Code)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2275. Min Range: -4.2275
Max Act: 3.4079. Min Act: -0.0001
Data Index: 216980 (C4 (Web Text))
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2275. Min Range: -4.2275
Max Act: 3.8621. Min Act: -0.0001
Data Index: 861298 (C4 (Web Text))
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2275. Min Range: -4.2275
Max Act: 3.8214. Min Act: -0.0001
Data Index: 968326 (C4 (Web Text))
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2275. Min Range: -4.2275
Max Act: 3.4695. Min Act: -0.0001
Data Index: 917446 (C4 (Web Text))
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2275. Min Range: -4.2275
Max Act: 3.0189. Min Act: -0.0001
Data Index: 856011 (C4 (Web Text))
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2275. Min Range: -4.2275
Max Act: 3.3046. Min Act: -0.0001
Data Index: 431590 (C4 (Web Text))
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2275. Min Range: -4.2275
Max Act: 2.8661. Min Act: -0.0001
Data Index: 643777 (C4 (Web Text))
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2275. Min Range: -4.2275
Max Act: 3.3992. Min Act: -0.0001
Data Index: 862358 (C4 (Web Text))
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #19