Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3067 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6630. Min Range: -7.6630
Max Act: 7.6630. Min Act: -0.1700
Data Index: 4302248 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6630. Min Range: -7.6630
Max Act: 7.4442. Min Act: -0.1700
Data Index: 3197888 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6630. Min Range: -7.6630
Max Act: 7.3192. Min Act: -0.1700
Data Index: 4247564 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6630. Min Range: -7.6630
Max Act: 7.3192. Min Act: -0.1700
Data Index: 4292067 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6630. Min Range: -7.6630
Max Act: 7.2880. Min Act: -0.1700
Data Index: 4292058 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6630. Min Range: -7.6630
Max Act: 7.1942. Min Act: -0.1700
Data Index: 6541400 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6630. Min Range: -7.6630
Max Act: 7.1005. Min Act: -0.1700
Data Index: 5659765 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6630. Min Range: -7.6630
Max Act: 7.1317. Min Act: -0.1700
Data Index: 4247551 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6630. Min Range: -7.6630
Max Act: 7.1317. Min Act: -0.1700
Data Index: 8327736 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6630. Min Range: -7.6630
Max Act: 7.0067. Min Act: -0.1700
Data Index: 5748995 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6630. Min Range: -7.6630
Max Act: 7.0067. Min Act: -0.1700
Data Index: 7199785 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6630. Min Range: -7.6630
Max Act: 6.9755. Min Act: -0.1700
Data Index: 5361245 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6630. Min Range: -7.6630
Max Act: 7.0067. Min Act: -0.1700
Data Index: 4139221 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6630. Min Range: -7.6630
Max Act: 6.9442. Min Act: -0.1700
Data Index: 6617574 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6630. Min Range: -7.6630
Max Act: 6.9442. Min Act: -0.1700
Data Index: 1403843 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6630. Min Range: -7.6630
Max Act: 6.8505. Min Act: -0.1700
Data Index: 300255 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6630. Min Range: -7.6630
Max Act: 6.8192. Min Act: -0.1700
Data Index: 2304621 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6630. Min Range: -7.6630
Max Act: 6.8505. Min Act: -0.1700
Data Index: 1447207 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6630. Min Range: -7.6630
Max Act: 6.8192. Min Act: -0.1700
Data Index: 7087762 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6630. Min Range: -7.6630
Max Act: 6.8192. Min Act: -0.1700
Data Index: 1403858 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #19