Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2018 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 4.5301. Min Range: -4.5301
Max Act: 4.5301. Min Act: -0.1700
Data Index: 569943 (C4 (Web Text))
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5301. Min Range: -4.5301
Max Act: 4.3738. Min Act: -0.1700
Data Index: 886724 (C4 (Web Text))
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5301. Min Range: -4.5301
Max Act: 4.2801. Min Act: -0.1700
Data Index: 720258 (C4 (Web Text))
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5301. Min Range: -4.5301
Max Act: 4.2488. Min Act: -0.1700
Data Index: 233096 (C4 (Web Text))
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5301. Min Range: -4.5301
Max Act: 4.2801. Min Act: -0.1700
Data Index: 949264 (C4 (Web Text))
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5301. Min Range: -4.5301
Max Act: 4.2488. Min Act: -0.1700
Data Index: 455422 (C4 (Web Text))
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5301. Min Range: -4.5301
Max Act: 4.2176. Min Act: -0.1700
Data Index: 10895 (C4 (Web Text))
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5301. Min Range: -4.5301
Max Act: 4.2176. Min Act: -0.1700
Data Index: 46930 (C4 (Web Text))
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5301. Min Range: -4.5301
Max Act: 4.2176. Min Act: -0.1700
Data Index: 881089 (C4 (Web Text))
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5301. Min Range: -4.5301
Max Act: 4.2488. Min Act: -0.1700
Data Index: 502024 (C4 (Web Text))
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5301. Min Range: -4.5301
Max Act: 4.1863. Min Act: -0.1700
Data Index: 282816 (C4 (Web Text))
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5301. Min Range: -4.5301
Max Act: 4.2176. Min Act: -0.1700
Data Index: 895298 (C4 (Web Text))
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5301. Min Range: -4.5301
Max Act: 4.1863. Min Act: -0.1700
Data Index: 1309280 (C4 (Web Text))
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5301. Min Range: -4.5301
Max Act: 4.1863. Min Act: -0.1700
Data Index: 1091367 (C4 (Web Text))
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5301. Min Range: -4.5301
Max Act: 4.1550. Min Act: -0.1700
Data Index: 756637 (C4 (Web Text))
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5301. Min Range: -4.5301
Max Act: 4.1550. Min Act: -0.1700
Data Index: 1304736 (C4 (Web Text))
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5301. Min Range: -4.5301
Max Act: 4.2488. Min Act: -0.1700
Data Index: 1041068 (C4 (Web Text))
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5301. Min Range: -4.5301
Max Act: 4.1550. Min Act: -0.1700
Data Index: 918348 (C4 (Web Text))
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5301. Min Range: -4.5301
Max Act: 4.1550. Min Act: -0.1700
Data Index: 1203997 (C4 (Web Text))
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5301. Min Range: -4.5301
Max Act: 4.1550. Min Act: -0.1700
Data Index: 1233524 (C4 (Web Text))
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #19