Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4754 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.9576. Min Range: -2.9576
Max Act: 2.9576. Min Act: -0.1700
Data Index: 1752770 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9576. Min Range: -2.9576
Max Act: 2.7510. Min Act: -0.1700
Data Index: 8164774 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9576. Min Range: -2.9576
Max Act: 2.7190. Min Act: -0.1700
Data Index: 4962156 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9576. Min Range: -2.9576
Max Act: 2.6870. Min Act: -0.1700
Data Index: 691254 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9576. Min Range: -2.9576
Max Act: 2.6389. Min Act: -0.1700
Data Index: 4962147 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9576. Min Range: -2.9576
Max Act: 2.6389. Min Act: -0.1700
Data Index: 4431303 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9576. Min Range: -2.9576
Max Act: 2.6389. Min Act: -0.1700
Data Index: 4581139 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9576. Min Range: -2.9576
Max Act: 2.6550. Min Act: -0.1700
Data Index: 3452813 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9576. Min Range: -2.9576
Max Act: 2.6229. Min Act: -0.1700
Data Index: 404291 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9576. Min Range: -2.9576
Max Act: 2.6389. Min Act: -0.1700
Data Index: 7838606 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9576. Min Range: -2.9576
Max Act: 2.5907. Min Act: -0.1700
Data Index: 7275319 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9576. Min Range: -2.9576
Max Act: 2.5746. Min Act: -0.1700
Data Index: 3346921 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9576. Min Range: -2.9576
Max Act: 2.5907. Min Act: -0.1700
Data Index: 5267628 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9576. Min Range: -2.9576
Max Act: 2.5261. Min Act: -0.1700
Data Index: 7270641 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9576. Min Range: -2.9576
Max Act: 2.5100. Min Act: -0.1700
Data Index: 3156264 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9576. Min Range: -2.9576
Max Act: 2.5261. Min Act: -0.1700
Data Index: 6165287 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9576. Min Range: -2.9576
Max Act: 2.5100. Min Act: -0.1700
Data Index: 6492860 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9576. Min Range: -2.9576
Max Act: 2.5100. Min Act: -0.1700
Data Index: 3674841 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9576. Min Range: -2.9576
Max Act: 2.5100. Min Act: -0.1700
Data Index: 796448 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9576. Min Range: -2.9576
Max Act: 2.5100. Min Act: -0.1700
Data Index: 365857 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #19