Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2618 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 2.7246. Min Range: -2.7246
Max Act: 2.6354. Min Act: -0.0001
Data Index: 1210800 (C4 (Web Text))
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7246. Min Range: -2.7246
Max Act: 2.4816. Min Act: -0.0001
Data Index: 854016 (C4 (Web Text))
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7246. Min Range: -2.7246
Max Act: 2.7246. Min Act: -0.0001
Data Index: 877425 (C4 (Web Text))
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7246. Min Range: -2.7246
Max Act: 2.6280. Min Act: -0.0001
Data Index: 268262 (C4 (Web Text))
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7246. Min Range: -2.7246
Max Act: 2.5944. Min Act: -0.0001
Data Index: 764787 (C4 (Web Text))
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7246. Min Range: -2.7246
Max Act: 2.6060. Min Act: -0.0001
Data Index: 395846 (C4 (Web Text))
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7246. Min Range: -2.7246
Max Act: 2.5835. Min Act: -0.0001
Data Index: 1058702 (C4 (Web Text))
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7246. Min Range: -2.7246
Max Act: 2.7044. Min Act: -0.0001
Data Index: 677706 (C4 (Web Text))
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7246. Min Range: -2.7246
Max Act: 2.4178. Min Act: -0.0001
Data Index: 1088615 (C4 (Web Text))
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7246. Min Range: -2.7246
Max Act: 2.4260. Min Act: -0.0001
Data Index: 128863 (C4 (Web Text))
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7246. Min Range: -2.7246
Max Act: 2.6501. Min Act: -0.0001
Data Index: 568102 (C4 (Web Text))
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7246. Min Range: -2.7246
Max Act: 2.5306. Min Act: -0.0001
Data Index: 1207424 (C4 (Web Text))
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7246. Min Range: -2.7246
Max Act: 2.5389. Min Act: -0.0001
Data Index: 739177 (C4 (Web Text))
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7246. Min Range: -2.7246
Max Act: 2.5093. Min Act: -0.0001
Data Index: 1109273 (C4 (Web Text))
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7246. Min Range: -2.7246
Max Act: 2.4929. Min Act: -0.0001
Data Index: 1025042 (C4 (Web Text))
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7246. Min Range: -2.7246
Max Act: 2.4449. Min Act: -0.0001
Data Index: 430137 (C4 (Web Text))
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7246. Min Range: -2.7246
Max Act: 2.5651. Min Act: -0.0001
Data Index: 914985 (C4 (Web Text))
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7246. Min Range: -2.7246
Max Act: 2.5487. Min Act: -0.0001
Data Index: 1344639 (C4 (Web Text))
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7246. Min Range: -2.7246
Max Act: 2.4277. Min Act: -0.0001
Data Index: 874314 (C4 (Web Text))
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7246. Min Range: -2.7246
Max Act: 2.3644. Min Act: -0.0001
Data Index: 1175680 (C4 (Web Text))
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #19