Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1929 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 2.7383. Min Range: -2.7383
Max Act: 2.7383. Min Act: -0.1700
Data Index: 260289 (C4 (Web Text))
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7383. Min Range: -2.7383
Max Act: 2.7223. Min Act: -0.1700
Data Index: 512590 (C4 (Web Text))
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7383. Min Range: -2.7383
Max Act: 2.6583. Min Act: -0.1700
Data Index: 259403 (C4 (Web Text))
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7383. Min Range: -2.7383
Max Act: 2.5940. Min Act: -0.1700
Data Index: 817589 (C4 (Web Text))
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7383. Min Range: -2.7383
Max Act: 2.5940. Min Act: -0.1700
Data Index: 333606 (C4 (Web Text))
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7383. Min Range: -2.7383
Max Act: 2.6101. Min Act: -0.1700
Data Index: 1231562 (C4 (Web Text))
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7383. Min Range: -2.7383
Max Act: 2.5779. Min Act: -0.1700
Data Index: 417466 (C4 (Web Text))
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7383. Min Range: -2.7383
Max Act: 2.5618. Min Act: -0.1700
Data Index: 851665 (C4 (Web Text))
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7383. Min Range: -2.7383
Max Act: 2.5295. Min Act: -0.1700
Data Index: 1442047 (Python Code)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7383. Min Range: -2.7383
Max Act: 2.5295. Min Act: -0.1700
Data Index: 736345 (C4 (Web Text))
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7383. Min Range: -2.7383
Max Act: 2.5457. Min Act: -0.1700
Data Index: 813540 (C4 (Web Text))
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7383. Min Range: -2.7383
Max Act: 2.5133. Min Act: -0.1700
Data Index: 400561 (C4 (Web Text))
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7383. Min Range: -2.7383
Max Act: 2.5295. Min Act: -0.1700
Data Index: 1098000 (C4 (Web Text))
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7383. Min Range: -2.7383
Max Act: 2.5133. Min Act: -0.1700
Data Index: 979194 (C4 (Web Text))
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7383. Min Range: -2.7383
Max Act: 2.5133. Min Act: -0.1700
Data Index: 902055 (C4 (Web Text))
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7383. Min Range: -2.7383
Max Act: 2.5457. Min Act: -0.1700
Data Index: 905877 (C4 (Web Text))
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7383. Min Range: -2.7383
Max Act: 2.5133. Min Act: -0.1700
Data Index: 1573955 (Python Code)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7383. Min Range: -2.7383
Max Act: 2.4809. Min Act: -0.1700
Data Index: 375457 (C4 (Web Text))
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7383. Min Range: -2.7383
Max Act: 2.4971. Min Act: -0.1700
Data Index: 692208 (C4 (Web Text))
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7383. Min Range: -2.7383
Max Act: 2.4971. Min Act: -0.1700
Data Index: 1156643 (C4 (Web Text))
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #19