Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 30 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 4.9762. Min Range: -4.9762
Max Act: 4.8824. Min Act: -0.1700
Data Index: 901566 (C4 (Web Text))
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9762. Min Range: -4.9762
Max Act: 4.9762. Min Act: -0.1700
Data Index: 1053217 (C4 (Web Text))
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9762. Min Range: -4.9762
Max Act: 4.8512. Min Act: -0.1700
Data Index: 72521 (C4 (Web Text))
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9762. Min Range: -4.9762
Max Act: 4.8199. Min Act: -0.1700
Data Index: 1144590 (C4 (Web Text))
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9762. Min Range: -4.9762
Max Act: 4.7574. Min Act: -0.1700
Data Index: 1019961 (C4 (Web Text))
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9762. Min Range: -4.9762
Max Act: 4.7887. Min Act: -0.1700
Data Index: 454777 (C4 (Web Text))
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9762. Min Range: -4.9762
Max Act: 4.7574. Min Act: -0.1700
Data Index: 222834 (C4 (Web Text))
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9762. Min Range: -4.9762
Max Act: 4.7262. Min Act: -0.1700
Data Index: 177724 (C4 (Web Text))
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9762. Min Range: -4.9762
Max Act: 4.6949. Min Act: -0.1700
Data Index: 50314 (C4 (Web Text))
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9762. Min Range: -4.9762
Max Act: 4.6637. Min Act: -0.1700
Data Index: 652363 (C4 (Web Text))
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9762. Min Range: -4.9762
Max Act: 4.6949. Min Act: -0.1700
Data Index: 574408 (C4 (Web Text))
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9762. Min Range: -4.9762
Max Act: 4.6637. Min Act: -0.1700
Data Index: 167082 (C4 (Web Text))
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9762. Min Range: -4.9762
Max Act: 4.6637. Min Act: -0.1700
Data Index: 514640 (C4 (Web Text))
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9762. Min Range: -4.9762
Max Act: 4.6637. Min Act: -0.1700
Data Index: 886551 (C4 (Web Text))
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9762. Min Range: -4.9762
Max Act: 4.6324. Min Act: -0.1700
Data Index: 1305536 (C4 (Web Text))
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9762. Min Range: -4.9762
Max Act: 4.6637. Min Act: -0.1700
Data Index: 312932 (C4 (Web Text))
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9762. Min Range: -4.9762
Max Act: 4.6324. Min Act: -0.1700
Data Index: 613745 (C4 (Web Text))
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9762. Min Range: -4.9762
Max Act: 4.6324. Min Act: -0.1700
Data Index: 524522 (C4 (Web Text))
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9762. Min Range: -4.9762
Max Act: 4.6012. Min Act: -0.1700
Data Index: 1099603 (C4 (Web Text))
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9762. Min Range: -4.9762
Max Act: 4.5699. Min Act: -0.1700
Data Index: 965197 (C4 (Web Text))
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #19