Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3640 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8659. Min Range: -4.8659
Max Act: 4.8659. Min Act: -0.1700
Data Index: 4154695 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8659. Min Range: -4.8659
Max Act: 4.6159. Min Act: -0.1700
Data Index: 3273395 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8659. Min Range: -4.8659
Max Act: 4.5846. Min Act: -0.1700
Data Index: 1097873 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8659. Min Range: -4.8659
Max Act: 4.5221. Min Act: -0.1700
Data Index: 3916954 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8659. Min Range: -4.8659
Max Act: 4.5221. Min Act: -0.1700
Data Index: 3814700 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8659. Min Range: -4.8659
Max Act: 4.5221. Min Act: -0.1700
Data Index: 2460479 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8659. Min Range: -4.8659
Max Act: 4.4909. Min Act: -0.1700
Data Index: 625791 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8659. Min Range: -4.8659
Max Act: 4.4909. Min Act: -0.1700
Data Index: 434912 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8659. Min Range: -4.8659
Max Act: 4.4596. Min Act: -0.1700
Data Index: 1529136 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8659. Min Range: -4.8659
Max Act: 4.4596. Min Act: -0.1700
Data Index: 6610812 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8659. Min Range: -4.8659
Max Act: 4.4596. Min Act: -0.1700
Data Index: 566764 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8659. Min Range: -4.8659
Max Act: 4.4284. Min Act: -0.1700
Data Index: 2883939 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8659. Min Range: -4.8659
Max Act: 4.4284. Min Act: -0.1700
Data Index: 8387743 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8659. Min Range: -4.8659
Max Act: 4.3971. Min Act: -0.1700
Data Index: 7918431 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8659. Min Range: -4.8659
Max Act: 4.3971. Min Act: -0.1700
Data Index: 8410198 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8659. Min Range: -4.8659
Max Act: 4.3659. Min Act: -0.1700
Data Index: 1239375 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8659. Min Range: -4.8659
Max Act: 4.3659. Min Act: -0.1700
Data Index: 7410838 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8659. Min Range: -4.8659
Max Act: 4.3346. Min Act: -0.1700
Data Index: 4434094 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8659. Min Range: -4.8659
Max Act: 4.3659. Min Act: -0.1700
Data Index: 1279671 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8659. Min Range: -4.8659
Max Act: 4.3346. Min Act: -0.1700
Data Index: 2069515 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #19