Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1925 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8173. Min Range: -5.8173
Max Act: 5.8173. Min Act: -0.1700
Data Index: 4571538 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8173. Min Range: -5.8173
Max Act: 5.6611. Min Act: -0.1700
Data Index: 109744 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8173. Min Range: -5.8173
Max Act: 5.6298. Min Act: -0.1700
Data Index: 4715566 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8173. Min Range: -5.8173
Max Act: 5.5048. Min Act: -0.1700
Data Index: 28198 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8173. Min Range: -5.8173
Max Act: 5.4736. Min Act: -0.1700
Data Index: 1344876 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8173. Min Range: -5.8173
Max Act: 5.4423. Min Act: -0.1700
Data Index: 6894495 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8173. Min Range: -5.8173
Max Act: 5.4423. Min Act: -0.1700
Data Index: 2416134 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8173. Min Range: -5.8173
Max Act: 5.4423. Min Act: -0.1700
Data Index: 3500263 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8173. Min Range: -5.8173
Max Act: 5.4111. Min Act: -0.1700
Data Index: 1504124 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8173. Min Range: -5.8173
Max Act: 5.3798. Min Act: -0.1700
Data Index: 4911954 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8173. Min Range: -5.8173
Max Act: 5.3798. Min Act: -0.1700
Data Index: 1940665 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8173. Min Range: -5.8173
Max Act: 5.3798. Min Act: -0.1700
Data Index: 2170695 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8173. Min Range: -5.8173
Max Act: 5.4111. Min Act: -0.1700
Data Index: 8556750 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8173. Min Range: -5.8173
Max Act: 5.3798. Min Act: -0.1700
Data Index: 2869968 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8173. Min Range: -5.8173
Max Act: 5.3798. Min Act: -0.1700
Data Index: 6479552 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8173. Min Range: -5.8173
Max Act: 5.3798. Min Act: -0.1700
Data Index: 6667812 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8173. Min Range: -5.8173
Max Act: 5.3798. Min Act: -0.1700
Data Index: 4906756 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8173. Min Range: -5.8173
Max Act: 5.3486. Min Act: -0.1700
Data Index: 887523 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8173. Min Range: -5.8173
Max Act: 5.3486. Min Act: -0.1700
Data Index: 5106810 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8173. Min Range: -5.8173
Max Act: 5.3173. Min Act: -0.1700
Data Index: 4249798 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #19