Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 59 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.8303. Min Range: -4.8303
Max Act: 4.7991. Min Act: -0.1700
Data Index: 307627 (C4 (Web Text))
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8303. Min Range: -4.8303
Max Act: 4.8303. Min Act: -0.1700
Data Index: 1304502 (C4 (Web Text))
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8303. Min Range: -4.8303
Max Act: 4.7053. Min Act: -0.1700
Data Index: 539818 (C4 (Web Text))
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8303. Min Range: -4.8303
Max Act: 4.6428. Min Act: -0.1700
Data Index: 261311 (C4 (Web Text))
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8303. Min Range: -4.8303
Max Act: 4.5803. Min Act: -0.1700
Data Index: 722442 (C4 (Web Text))
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8303. Min Range: -4.8303
Max Act: 4.6428. Min Act: -0.1700
Data Index: 1231828 (C4 (Web Text))
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8303. Min Range: -4.8303
Max Act: 4.5803. Min Act: -0.1700
Data Index: 1268315 (C4 (Web Text))
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8303. Min Range: -4.8303
Max Act: 4.5178. Min Act: -0.1700
Data Index: 1227424 (C4 (Web Text))
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8303. Min Range: -4.8303
Max Act: 4.5803. Min Act: -0.1700
Data Index: 747748 (C4 (Web Text))
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8303. Min Range: -4.8303
Max Act: 4.4240. Min Act: -0.1700
Data Index: 748275 (C4 (Web Text))
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8303. Min Range: -4.8303
Max Act: 4.5491. Min Act: -0.1700
Data Index: 804268 (C4 (Web Text))
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8303. Min Range: -4.8303
Max Act: 4.5803. Min Act: -0.1700
Data Index: 1123741 (C4 (Web Text))
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8303. Min Range: -4.8303
Max Act: 4.5178. Min Act: -0.1700
Data Index: 1348203 (C4 (Web Text))
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8303. Min Range: -4.8303
Max Act: 4.5178. Min Act: -0.1700
Data Index: 417579 (C4 (Web Text))
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8303. Min Range: -4.8303
Max Act: 4.4865. Min Act: -0.1700
Data Index: 734807 (C4 (Web Text))
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8303. Min Range: -4.8303
Max Act: 4.4865. Min Act: -0.1700
Data Index: 311120 (C4 (Web Text))
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8303. Min Range: -4.8303
Max Act: 4.5491. Min Act: -0.1700
Data Index: 941504 (C4 (Web Text))
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8303. Min Range: -4.8303
Max Act: 4.4865. Min Act: -0.1700
Data Index: 412276 (C4 (Web Text))
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8303. Min Range: -4.8303
Max Act: 4.4240. Min Act: -0.1700
Data Index: 650977 (C4 (Web Text))
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8303. Min Range: -4.8303
Max Act: 4.3928. Min Act: -0.1700
Data Index: 393604 (C4 (Web Text))
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #19