Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2024 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 3.7131. Min Range: -3.7131
Max Act: 3.7131. Min Act: -0.1700
Data Index: 1587426 (Python Code)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7131. Min Range: -3.7131
Max Act: 3.7131. Min Act: -0.1700
Data Index: 1481274 (Python Code)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7131. Min Range: -3.7131
Max Act: 3.5879. Min Act: -0.1700
Data Index: 1344924 (C4 (Web Text))
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7131. Min Range: -3.7131
Max Act: 3.5566. Min Act: -0.1700
Data Index: 76722 (C4 (Web Text))
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7131. Min Range: -3.7131
Max Act: 3.5253. Min Act: -0.1700
Data Index: 55364 (C4 (Web Text))
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7131. Min Range: -3.7131
Max Act: 3.5253. Min Act: -0.1700
Data Index: 1391209 (Python Code)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7131. Min Range: -3.7131
Max Act: 3.5566. Min Act: -0.1700
Data Index: 1073918 (C4 (Web Text))
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7131. Min Range: -3.7131
Max Act: 3.5253. Min Act: -0.1700
Data Index: 1304841 (C4 (Web Text))
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7131. Min Range: -3.7131
Max Act: 3.5253. Min Act: -0.1700
Data Index: 812089 (C4 (Web Text))
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7131. Min Range: -3.7131
Max Act: 3.5253. Min Act: -0.1700
Data Index: 1507554 (Python Code)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7131. Min Range: -3.7131
Max Act: 3.5096. Min Act: -0.1700
Data Index: 1309555 (C4 (Web Text))
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7131. Min Range: -3.7131
Max Act: 3.4783. Min Act: -0.1700
Data Index: 1419562 (Python Code)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7131. Min Range: -3.7131
Max Act: 3.4626. Min Act: -0.1700
Data Index: 852970 (C4 (Web Text))
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7131. Min Range: -3.7131
Max Act: 3.4783. Min Act: -0.1700
Data Index: 1252232 (C4 (Web Text))
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7131. Min Range: -3.7131
Max Act: 3.4469. Min Act: -0.1700
Data Index: 1516736 (Python Code)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7131. Min Range: -3.7131
Max Act: 3.4626. Min Act: -0.1700
Data Index: 823484 (C4 (Web Text))
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7131. Min Range: -3.7131
Max Act: 3.4469. Min Act: -0.1700
Data Index: 683028 (C4 (Web Text))
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7131. Min Range: -3.7131
Max Act: 3.4312. Min Act: -0.1700
Data Index: 1458658 (Python Code)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7131. Min Range: -3.7131
Max Act: 3.4469. Min Act: -0.1700
Data Index: 55890 (C4 (Web Text))
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7131. Min Range: -3.7131
Max Act: 3.4469. Min Act: -0.1700
Data Index: 643716 (C4 (Web Text))
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #19