Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5548. Min Range: -5.5548
Max Act: 5.5548. Min Act: -0.1700
Data Index: 6048555 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5548. Min Range: -5.5548
Max Act: 5.3673. Min Act: -0.1700
Data Index: 6517496 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5548. Min Range: -5.5548
Max Act: 5.3986. Min Act: -0.1700
Data Index: 6920718 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5548. Min Range: -5.5548
Max Act: 5.2736. Min Act: -0.1700
Data Index: 6184247 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5548. Min Range: -5.5548
Max Act: 5.2423. Min Act: -0.1700
Data Index: 7785455 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5548. Min Range: -5.5548
Max Act: 5.1798. Min Act: -0.1700
Data Index: 3278488 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5548. Min Range: -5.5548
Max Act: 5.1798. Min Act: -0.1700
Data Index: 4770602 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5548. Min Range: -5.5548
Max Act: 5.0861. Min Act: -0.1700
Data Index: 391837 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5548. Min Range: -5.5548
Max Act: 5.0548. Min Act: -0.1700
Data Index: 903741 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5548. Min Range: -5.5548
Max Act: 5.0548. Min Act: -0.1700
Data Index: 4558701 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5548. Min Range: -5.5548
Max Act: 5.0548. Min Act: -0.1700
Data Index: 362028 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5548. Min Range: -5.5548
Max Act: 5.0861. Min Act: -0.1700
Data Index: 720881 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5548. Min Range: -5.5548
Max Act: 5.0861. Min Act: -0.1700
Data Index: 131481 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5548. Min Range: -5.5548
Max Act: 5.0236. Min Act: -0.1700
Data Index: 6031266 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5548. Min Range: -5.5548
Max Act: 4.9923. Min Act: -0.1700
Data Index: 6610308 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5548. Min Range: -5.5548
Max Act: 4.9923. Min Act: -0.1700
Data Index: 6600572 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5548. Min Range: -5.5548
Max Act: 4.9923. Min Act: -0.1700
Data Index: 5826559 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5548. Min Range: -5.5548
Max Act: 4.9923. Min Act: -0.1700
Data Index: 2400305 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5548. Min Range: -5.5548
Max Act: 4.9611. Min Act: -0.1700
Data Index: 5795021 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5548. Min Range: -5.5548
Max Act: 4.9611. Min Act: -0.1700
Data Index: 7258694 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #19