Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2723 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.9522. Min Range: -4.9522
Max Act: 4.9522. Min Act: -0.1700
Data Index: 90498 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9522. Min Range: -4.9522
Max Act: 4.8585. Min Act: -0.1700
Data Index: 8441459 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9522. Min Range: -4.9522
Max Act: 4.8585. Min Act: -0.1700
Data Index: 8136368 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9522. Min Range: -4.9522
Max Act: 4.8585. Min Act: -0.1700
Data Index: 5045020 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9522. Min Range: -4.9522
Max Act: 4.8585. Min Act: -0.1700
Data Index: 2038415 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9522. Min Range: -4.9522
Max Act: 4.7960. Min Act: -0.1700
Data Index: 6584257 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9522. Min Range: -4.9522
Max Act: 4.7960. Min Act: -0.1700
Data Index: 4995465 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9522. Min Range: -4.9522
Max Act: 4.7960. Min Act: -0.1700
Data Index: 2243831 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9522. Min Range: -4.9522
Max Act: 4.7960. Min Act: -0.1700
Data Index: 6977973 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9522. Min Range: -4.9522
Max Act: 4.7647. Min Act: -0.1700
Data Index: 3576309 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9522. Min Range: -4.9522
Max Act: 4.7960. Min Act: -0.1700
Data Index: 381301 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9522. Min Range: -4.9522
Max Act: 4.7647. Min Act: -0.1700
Data Index: 6816685 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9522. Min Range: -4.9522
Max Act: 4.7647. Min Act: -0.1700
Data Index: 4467378 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9522. Min Range: -4.9522
Max Act: 4.7647. Min Act: -0.1700
Data Index: 2243833 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9522. Min Range: -4.9522
Max Act: 4.7647. Min Act: -0.1700
Data Index: 7111489 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9522. Min Range: -4.9522
Max Act: 4.7647. Min Act: -0.1700
Data Index: 5302071 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9522. Min Range: -4.9522
Max Act: 4.7335. Min Act: -0.1700
Data Index: 8075804 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9522. Min Range: -4.9522
Max Act: 4.7335. Min Act: -0.1700
Data Index: 181214 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9522. Min Range: -4.9522
Max Act: 4.7335. Min Act: -0.1700
Data Index: 563038 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9522. Min Range: -4.9522
Max Act: 4.7335. Min Act: -0.1700
Data Index: 4010200 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #19