Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1004 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 0.9912. Min Range: -0.9912
Max Act: 0.9912. Min Act: -0.0001
Data Index: 334499 (C4 (Web Text))
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.9912. Min Range: -0.9912
Max Act: 0.8735. Min Act: -0.0001
Data Index: 324249 (C4 (Web Text))
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.9912. Min Range: -0.9912
Max Act: 0.7462. Min Act: -0.0001
Data Index: 1255423 (C4 (Web Text))
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.9912. Min Range: -0.9912
Max Act: 0.7835. Min Act: -0.0001
Data Index: 1187024 (C4 (Web Text))
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.9912. Min Range: -0.9912
Max Act: 0.7974. Min Act: -0.0001
Data Index: 1175233 (C4 (Web Text))
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.9912. Min Range: -0.9912
Max Act: 0.7709. Min Act: -0.0001
Data Index: 524411 (C4 (Web Text))
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.9912. Min Range: -0.9912
Max Act: 0.7349. Min Act: -0.0001
Data Index: 406254 (C4 (Web Text))
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.9912. Min Range: -0.9912
Max Act: 0.7190. Min Act: -0.0001
Data Index: 492103 (C4 (Web Text))
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.9912. Min Range: -0.9912
Max Act: 0.7038. Min Act: -0.0001
Data Index: 649562 (C4 (Web Text))
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.9912. Min Range: -0.9912
Max Act: 0.7271. Min Act: -0.0001
Data Index: 110144 (C4 (Web Text))
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.9912. Min Range: -0.9912
Max Act: 0.7489. Min Act: -0.0001
Data Index: 152720 (C4 (Web Text))
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.9912. Min Range: -0.9912
Max Act: 0.6612. Min Act: -0.0001
Data Index: 252477 (C4 (Web Text))
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.9912. Min Range: -0.9912
Max Act: 0.7117. Min Act: -0.0001
Data Index: 15382 (C4 (Web Text))
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.9912. Min Range: -0.9912
Max Act: 0.7341. Min Act: -0.0001
Data Index: 626944 (C4 (Web Text))
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.9912. Min Range: -0.9912
Max Act: 0.6834. Min Act: -0.0001
Data Index: 397005 (C4 (Web Text))
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.9912. Min Range: -0.9912
Max Act: 0.6811. Min Act: -0.0001
Data Index: 1351609 (C4 (Web Text))
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.9912. Min Range: -0.9912
Max Act: 0.7262. Min Act: -0.0001
Data Index: 896382 (C4 (Web Text))
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.9912. Min Range: -0.9912
Max Act: 0.6569. Min Act: -0.0001
Data Index: 238741 (C4 (Web Text))
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.9912. Min Range: -0.9912
Max Act: 0.6940. Min Act: -0.0001
Data Index: 588217 (C4 (Web Text))
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.9912. Min Range: -0.9912
Max Act: 0.6510. Min Act: -0.0001
Data Index: 240042 (C4 (Web Text))
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #19