Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 475 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7232. Min Range: -7.7232
Max Act: 7.7232. Min Act: -0.1700
Data Index: 2688038 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7232. Min Range: -7.7232
Max Act: 7.5669. Min Act: -0.1700
Data Index: 2189517 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7232. Min Range: -7.7232
Max Act: 7.5669. Min Act: -0.1700
Data Index: 6862812 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7232. Min Range: -7.7232
Max Act: 7.4107. Min Act: -0.1700
Data Index: 6675570 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7232. Min Range: -7.7232
Max Act: 7.2232. Min Act: -0.1700
Data Index: 1698423 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7232. Min Range: -7.7232
Max Act: 7.1607. Min Act: -0.1700
Data Index: 5391409 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7232. Min Range: -7.7232
Max Act: 7.1294. Min Act: -0.1700
Data Index: 2577422 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7232. Min Range: -7.7232
Max Act: 7.1607. Min Act: -0.1700
Data Index: 5817076 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7232. Min Range: -7.7232
Max Act: 7.1294. Min Act: -0.1700
Data Index: 7194642 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7232. Min Range: -7.7232
Max Act: 7.1294. Min Act: -0.1700
Data Index: 4451030 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7232. Min Range: -7.7232
Max Act: 7.1294. Min Act: -0.1700
Data Index: 5559188 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7232. Min Range: -7.7232
Max Act: 7.0357. Min Act: -0.1700
Data Index: 3138500 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7232. Min Range: -7.7232
Max Act: 7.0044. Min Act: -0.1700
Data Index: 5067456 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7232. Min Range: -7.7232
Max Act: 6.9732. Min Act: -0.1700
Data Index: 1310912 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7232. Min Range: -7.7232
Max Act: 6.9732. Min Act: -0.1700
Data Index: 6918662 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7232. Min Range: -7.7232
Max Act: 6.9732. Min Act: -0.1700
Data Index: 7757160 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7232. Min Range: -7.7232
Max Act: 6.9732. Min Act: -0.1700
Data Index: 3069764 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7232. Min Range: -7.7232
Max Act: 6.9419. Min Act: -0.1700
Data Index: 8185880 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7232. Min Range: -7.7232
Max Act: 6.9107. Min Act: -0.1700
Data Index: 3759942 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7232. Min Range: -7.7232
Max Act: 6.9107. Min Act: -0.1700
Data Index: 2925532 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #19