Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1617 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 4.7089. Min Range: -4.7089
Max Act: 4.7089. Min Act: -0.1700
Data Index: 1038638 (C4 (Web Text))
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7089. Min Range: -4.7089
Max Act: 4.5214. Min Act: -0.1700
Data Index: 363859 (C4 (Web Text))
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7089. Min Range: -4.7089
Max Act: 4.3339. Min Act: -0.1700
Data Index: 922568 (C4 (Web Text))
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7089. Min Range: -4.7089
Max Act: 4.3339. Min Act: -0.1700
Data Index: 1631322 (Python Code)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7089. Min Range: -4.7089
Max Act: 4.3339. Min Act: -0.1700
Data Index: 1179288 (C4 (Web Text))
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7089. Min Range: -4.7089
Max Act: 4.3652. Min Act: -0.1700
Data Index: 991408 (C4 (Web Text))
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7089. Min Range: -4.7089
Max Act: 4.2714. Min Act: -0.1700
Data Index: 414909 (C4 (Web Text))
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7089. Min Range: -4.7089
Max Act: 4.3339. Min Act: -0.1700
Data Index: 253300 (C4 (Web Text))
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7089. Min Range: -4.7089
Max Act: 4.3652. Min Act: -0.1700
Data Index: 1094752 (C4 (Web Text))
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7089. Min Range: -4.7089
Max Act: 4.2714. Min Act: -0.1700
Data Index: 1633451 (Python Code)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7089. Min Range: -4.7089
Max Act: 4.3027. Min Act: -0.1700
Data Index: 203674 (C4 (Web Text))
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7089. Min Range: -4.7089
Max Act: 4.3027. Min Act: -0.1700
Data Index: 434143 (C4 (Web Text))
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7089. Min Range: -4.7089
Max Act: 4.2714. Min Act: -0.1700
Data Index: 116751 (C4 (Web Text))
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7089. Min Range: -4.7089
Max Act: 4.2402. Min Act: -0.1700
Data Index: 1181031 (C4 (Web Text))
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7089. Min Range: -4.7089
Max Act: 4.3339. Min Act: -0.1700
Data Index: 703003 (C4 (Web Text))
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7089. Min Range: -4.7089
Max Act: 4.3027. Min Act: -0.1700
Data Index: 658192 (C4 (Web Text))
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7089. Min Range: -4.7089
Max Act: 4.3027. Min Act: -0.1700
Data Index: 1144052 (C4 (Web Text))
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7089. Min Range: -4.7089
Max Act: 4.2714. Min Act: -0.1700
Data Index: 344367 (C4 (Web Text))
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7089. Min Range: -4.7089
Max Act: 4.2089. Min Act: -0.1700
Data Index: 442355 (C4 (Web Text))
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7089. Min Range: -4.7089
Max Act: 4.2402. Min Act: -0.1700
Data Index: 1319034 (C4 (Web Text))
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #19