Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1280 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.4856. Min Range: -7.4856
Max Act: 7.4856. Min Act: -0.1700
Data Index: 1046360 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4856. Min Range: -7.4856
Max Act: 7.4544. Min Act: -0.1700
Data Index: 5311607 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4856. Min Range: -7.4856
Max Act: 7.4544. Min Act: -0.1700
Data Index: 6739716 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4856. Min Range: -7.4856
Max Act: 7.3919. Min Act: -0.1700
Data Index: 8634438 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4856. Min Range: -7.4856
Max Act: 7.3919. Min Act: -0.1700
Data Index: 5019746 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4856. Min Range: -7.4856
Max Act: 7.3606. Min Act: -0.1700
Data Index: 2970466 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4856. Min Range: -7.4856
Max Act: 7.3606. Min Act: -0.1700
Data Index: 3091717 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4856. Min Range: -7.4856
Max Act: 7.3606. Min Act: -0.1700
Data Index: 3718769 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4856. Min Range: -7.4856
Max Act: 7.3606. Min Act: -0.1700
Data Index: 5131230 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4856. Min Range: -7.4856
Max Act: 7.3606. Min Act: -0.1700
Data Index: 2692337 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4856. Min Range: -7.4856
Max Act: 7.3606. Min Act: -0.1700
Data Index: 6125773 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4856. Min Range: -7.4856
Max Act: 7.3294. Min Act: -0.1700
Data Index: 7511942 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4856. Min Range: -7.4856
Max Act: 7.2981. Min Act: -0.1700
Data Index: 6290946 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4856. Min Range: -7.4856
Max Act: 7.2981. Min Act: -0.1700
Data Index: 576321 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4856. Min Range: -7.4856
Max Act: 7.2981. Min Act: -0.1700
Data Index: 785343 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4856. Min Range: -7.4856
Max Act: 7.2669. Min Act: -0.1700
Data Index: 6694302 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4856. Min Range: -7.4856
Max Act: 7.2669. Min Act: -0.1700
Data Index: 356881 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4856. Min Range: -7.4856
Max Act: 7.2044. Min Act: -0.1700
Data Index: 3214047 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4856. Min Range: -7.4856
Max Act: 7.1731. Min Act: -0.1700
Data Index: 3177178 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4856. Min Range: -7.4856
Max Act: 7.1731. Min Act: -0.1700
Data Index: 7091088 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #19