Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2487 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4744. Min Range: -8.4744
Max Act: 8.4744. Min Act: -0.1700
Data Index: 1383977 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4744. Min Range: -8.4744
Max Act: 7.7869. Min Act: -0.1700
Data Index: 2099778 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4744. Min Range: -8.4744
Max Act: 7.7244. Min Act: -0.1700
Data Index: 5552142 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4744. Min Range: -8.4744
Max Act: 7.6619. Min Act: -0.1700
Data Index: 7523292 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4744. Min Range: -8.4744
Max Act: 7.5369. Min Act: -0.1700
Data Index: 3556082 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4744. Min Range: -8.4744
Max Act: 7.4744. Min Act: -0.1700
Data Index: 912007 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4744. Min Range: -8.4744
Max Act: 7.5056. Min Act: -0.1700
Data Index: 4757834 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4744. Min Range: -8.4744
Max Act: 7.4431. Min Act: -0.1700
Data Index: 4579007 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4744. Min Range: -8.4744
Max Act: 7.4119. Min Act: -0.1700
Data Index: 3556085 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4744. Min Range: -8.4744
Max Act: 7.3806. Min Act: -0.1700
Data Index: 4951033 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4744. Min Range: -8.4744
Max Act: 7.3806. Min Act: -0.1700
Data Index: 5247229 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4744. Min Range: -8.4744
Max Act: 7.3494. Min Act: -0.1700
Data Index: 3613763 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4744. Min Range: -8.4744
Max Act: 7.3494. Min Act: -0.1700
Data Index: 6506686 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4744. Min Range: -8.4744
Max Act: 7.3181. Min Act: -0.1700
Data Index: 1937214 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4744. Min Range: -8.4744
Max Act: 7.2869. Min Act: -0.1700
Data Index: 604585 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4744. Min Range: -8.4744
Max Act: 7.3181. Min Act: -0.1700
Data Index: 3200654 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4744. Min Range: -8.4744
Max Act: 7.3494. Min Act: -0.1700
Data Index: 1098772 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4744. Min Range: -8.4744
Max Act: 7.3181. Min Act: -0.1700
Data Index: 1098777 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4744. Min Range: -8.4744
Max Act: 7.2869. Min Act: -0.1700
Data Index: 1673039 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4744. Min Range: -8.4744
Max Act: 7.3181. Min Act: -0.1700
Data Index: 3556083 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #19