Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 261 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 4.1679. Min Range: -4.1679
Max Act: 4.1679. Min Act: -0.1700
Data Index: 1069792 (C4 (Web Text))
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1679. Min Range: -4.1679
Max Act: 3.6988. Min Act: -0.1700
Data Index: 1255929 (C4 (Web Text))
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1679. Min Range: -4.1679
Max Act: 3.6362. Min Act: -0.1700
Data Index: 1508380 (Python Code)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1679. Min Range: -4.1679
Max Act: 3.6362. Min Act: -0.1700
Data Index: 363456 (C4 (Web Text))
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1679. Min Range: -4.1679
Max Act: 3.6049. Min Act: -0.1700
Data Index: 79820 (C4 (Web Text))
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1679. Min Range: -4.1679
Max Act: 3.6049. Min Act: -0.1700
Data Index: 606031 (C4 (Web Text))
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1679. Min Range: -4.1679
Max Act: 3.5735. Min Act: -0.1700
Data Index: 1348931 (C4 (Web Text))
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1679. Min Range: -4.1679
Max Act: 3.5109. Min Act: -0.1700
Data Index: 1454103 (Python Code)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1679. Min Range: -4.1679
Max Act: 3.4482. Min Act: -0.1700
Data Index: 1106073 (C4 (Web Text))
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1679. Min Range: -4.1679
Max Act: 3.4796. Min Act: -0.1700
Data Index: 710313 (C4 (Web Text))
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1679. Min Range: -4.1679
Max Act: 3.5109. Min Act: -0.1700
Data Index: 1228481 (C4 (Web Text))
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1679. Min Range: -4.1679
Max Act: 3.5109. Min Act: -0.1700
Data Index: 655017 (C4 (Web Text))
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1679. Min Range: -4.1679
Max Act: 3.4796. Min Act: -0.1700
Data Index: 86659 (C4 (Web Text))
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1679. Min Range: -4.1679
Max Act: 3.4796. Min Act: -0.1700
Data Index: 786528 (C4 (Web Text))
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1679. Min Range: -4.1679
Max Act: 3.4796. Min Act: -0.1700
Data Index: 1204924 (C4 (Web Text))
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1679. Min Range: -4.1679
Max Act: 3.4796. Min Act: -0.1700
Data Index: 1476427 (Python Code)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1679. Min Range: -4.1679
Max Act: 3.4482. Min Act: -0.1700
Data Index: 250197 (C4 (Web Text))
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1679. Min Range: -4.1679
Max Act: 3.4168. Min Act: -0.1700
Data Index: 830987 (C4 (Web Text))
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1679. Min Range: -4.1679
Max Act: 3.4482. Min Act: -0.1700
Data Index: 1326442 (C4 (Web Text))
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1679. Min Range: -4.1679
Max Act: 3.4482. Min Act: -0.1700
Data Index: 377030 (C4 (Web Text))
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #19