Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 391 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.7933. Min Range: -4.7933
Max Act: 4.7620. Min Act: -0.1700
Data Index: 361303 (C4 (Web Text))
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7933. Min Range: -4.7933
Max Act: 4.7933. Min Act: -0.1700
Data Index: 404029 (C4 (Web Text))
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7933. Min Range: -4.7933
Max Act: 4.6683. Min Act: -0.1700
Data Index: 912921 (C4 (Web Text))
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7933. Min Range: -4.7933
Max Act: 4.6370. Min Act: -0.1700
Data Index: 1204968 (C4 (Web Text))
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7933. Min Range: -4.7933
Max Act: 4.6683. Min Act: -0.1700
Data Index: 1189123 (C4 (Web Text))
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7933. Min Range: -4.7933
Max Act: 4.6370. Min Act: -0.1700
Data Index: 192726 (C4 (Web Text))
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7933. Min Range: -4.7933
Max Act: 4.6683. Min Act: -0.1700
Data Index: 103415 (C4 (Web Text))
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7933. Min Range: -4.7933
Max Act: 4.6058. Min Act: -0.1700
Data Index: 1141858 (C4 (Web Text))
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7933. Min Range: -4.7933
Max Act: 4.5745. Min Act: -0.1700
Data Index: 1026742 (C4 (Web Text))
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7933. Min Range: -4.7933
Max Act: 4.5745. Min Act: -0.1700
Data Index: 917861 (C4 (Web Text))
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7933. Min Range: -4.7933
Max Act: 4.5433. Min Act: -0.1700
Data Index: 1114449 (C4 (Web Text))
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7933. Min Range: -4.7933
Max Act: 4.5745. Min Act: -0.1700
Data Index: 870361 (C4 (Web Text))
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7933. Min Range: -4.7933
Max Act: 4.5745. Min Act: -0.1700
Data Index: 283652 (C4 (Web Text))
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7933. Min Range: -4.7933
Max Act: 4.5120. Min Act: -0.1700
Data Index: 1147549 (C4 (Web Text))
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7933. Min Range: -4.7933
Max Act: 4.5745. Min Act: -0.1700
Data Index: 1177507 (C4 (Web Text))
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7933. Min Range: -4.7933
Max Act: 4.4808. Min Act: -0.1700
Data Index: 49964 (C4 (Web Text))
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7933. Min Range: -4.7933
Max Act: 4.5433. Min Act: -0.1700
Data Index: 162794 (C4 (Web Text))
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7933. Min Range: -4.7933
Max Act: 4.5745. Min Act: -0.1700
Data Index: 179785 (C4 (Web Text))
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7933. Min Range: -4.7933
Max Act: 4.5120. Min Act: -0.1700
Data Index: 722317 (C4 (Web Text))
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7933. Min Range: -4.7933
Max Act: 4.5120. Min Act: -0.1700
Data Index: 488061 (C4 (Web Text))
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #19