Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4940 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2808. Min Range: -6.2808
Max Act: 6.2808. Min Act: -0.1700
Data Index: 3285638 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2808. Min Range: -6.2808
Max Act: 5.9371. Min Act: -0.1700
Data Index: 7885564 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2808. Min Range: -6.2808
Max Act: 5.9058. Min Act: -0.1700
Data Index: 3324077 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2808. Min Range: -6.2808
Max Act: 5.9058. Min Act: -0.1700
Data Index: 103450 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2808. Min Range: -6.2808
Max Act: 5.8746. Min Act: -0.1700
Data Index: 3728496 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2808. Min Range: -6.2808
Max Act: 5.8433. Min Act: -0.1700
Data Index: 570824 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2808. Min Range: -6.2808
Max Act: 5.8746. Min Act: -0.1700
Data Index: 8795058 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2808. Min Range: -6.2808
Max Act: 5.8433. Min Act: -0.1700
Data Index: 4774850 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2808. Min Range: -6.2808
Max Act: 5.8746. Min Act: -0.1700
Data Index: 3974522 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2808. Min Range: -6.2808
Max Act: 5.8121. Min Act: -0.1700
Data Index: 7420519 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2808. Min Range: -6.2808
Max Act: 5.8121. Min Act: -0.1700
Data Index: 3663867 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2808. Min Range: -6.2808
Max Act: 5.8121. Min Act: -0.1700
Data Index: 1472894 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2808. Min Range: -6.2808
Max Act: 5.8121. Min Act: -0.1700
Data Index: 6262560 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2808. Min Range: -6.2808
Max Act: 5.8121. Min Act: -0.1700
Data Index: 3518318 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2808. Min Range: -6.2808
Max Act: 5.7808. Min Act: -0.1700
Data Index: 7649283 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2808. Min Range: -6.2808
Max Act: 5.7808. Min Act: -0.1700
Data Index: 2513019 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2808. Min Range: -6.2808
Max Act: 5.7808. Min Act: -0.1700
Data Index: 7201398 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2808. Min Range: -6.2808
Max Act: 5.7183. Min Act: -0.1700
Data Index: 8749257 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2808. Min Range: -6.2808
Max Act: 5.7496. Min Act: -0.1700
Data Index: 868458 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2808. Min Range: -6.2808
Max Act: 5.7496. Min Act: -0.1700
Data Index: 6957941 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #19