Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5009 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9681. Min Range: -5.9681
Max Act: 5.9681. Min Act: -0.1700
Data Index: 4851918 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9681. Min Range: -5.9681
Max Act: 5.9369. Min Act: -0.1700
Data Index: 3311696 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9681. Min Range: -5.9681
Max Act: 5.8431. Min Act: -0.1700
Data Index: 3400439 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9681. Min Range: -5.9681
Max Act: 5.8119. Min Act: -0.1700
Data Index: 2846104 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9681. Min Range: -5.9681
Max Act: 5.8119. Min Act: -0.1700
Data Index: 3799561 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9681. Min Range: -5.9681
Max Act: 5.8119. Min Act: -0.1700
Data Index: 8567584 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9681. Min Range: -5.9681
Max Act: 5.7806. Min Act: -0.1700
Data Index: 7893040 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9681. Min Range: -5.9681
Max Act: 5.7806. Min Act: -0.1700
Data Index: 4652659 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9681. Min Range: -5.9681
Max Act: 5.6869. Min Act: -0.1700
Data Index: 7249575 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9681. Min Range: -5.9681
Max Act: 5.6556. Min Act: -0.1700
Data Index: 6411860 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9681. Min Range: -5.9681
Max Act: 5.6556. Min Act: -0.1700
Data Index: 5763965 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9681. Min Range: -5.9681
Max Act: 5.6244. Min Act: -0.1700
Data Index: 3948803 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9681. Min Range: -5.9681
Max Act: 5.5931. Min Act: -0.1700
Data Index: 5840013 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9681. Min Range: -5.9681
Max Act: 5.5931. Min Act: -0.1700
Data Index: 4229125 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9681. Min Range: -5.9681
Max Act: 5.5931. Min Act: -0.1700
Data Index: 1066277 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9681. Min Range: -5.9681
Max Act: 5.5619. Min Act: -0.1700
Data Index: 522502 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9681. Min Range: -5.9681
Max Act: 5.5306. Min Act: -0.1700
Data Index: 6570408 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9681. Min Range: -5.9681
Max Act: 5.5619. Min Act: -0.1700
Data Index: 3287651 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9681. Min Range: -5.9681
Max Act: 5.5619. Min Act: -0.1700
Data Index: 5599436 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9681. Min Range: -5.9681
Max Act: 5.5306. Min Act: -0.1700
Data Index: 2802795 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #19