Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1572 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.7685. Min Range: -2.7685
Max Act: 2.7685. Min Act: -0.1700
Data Index: 360309 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7685. Min Range: -2.7685
Max Act: 2.6405. Min Act: -0.1700
Data Index: 360310 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7685. Min Range: -2.7685
Max Act: 2.6405. Min Act: -0.1700
Data Index: 995548 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7685. Min Range: -2.7685
Max Act: 2.6566. Min Act: -0.1700
Data Index: 8755144 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7685. Min Range: -2.7685
Max Act: 2.5923. Min Act: -0.1700
Data Index: 2570105 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7685. Min Range: -2.7685
Max Act: 2.5600. Min Act: -0.1700
Data Index: 8043722 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7685. Min Range: -2.7685
Max Act: 2.5439. Min Act: -0.1700
Data Index: 7599612 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7685. Min Range: -2.7685
Max Act: 2.5439. Min Act: -0.1700
Data Index: 5709173 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7685. Min Range: -2.7685
Max Act: 2.5600. Min Act: -0.1700
Data Index: 3292947 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7685. Min Range: -2.7685
Max Act: 2.5439. Min Act: -0.1700
Data Index: 4699880 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7685. Min Range: -2.7685
Max Act: 2.5439. Min Act: -0.1700
Data Index: 7509672 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7685. Min Range: -2.7685
Max Act: 2.5277. Min Act: -0.1700
Data Index: 1858100 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7685. Min Range: -2.7685
Max Act: 2.5277. Min Act: -0.1700
Data Index: 2237954 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7685. Min Range: -2.7685
Max Act: 2.5277. Min Act: -0.1700
Data Index: 8814811 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7685. Min Range: -2.7685
Max Act: 2.5277. Min Act: -0.1700
Data Index: 2695283 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7685. Min Range: -2.7685
Max Act: 2.5277. Min Act: -0.1700
Data Index: 3070811 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7685. Min Range: -2.7685
Max Act: 2.5277. Min Act: -0.1700
Data Index: 6869327 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7685. Min Range: -2.7685
Max Act: 2.5277. Min Act: -0.1700
Data Index: 6591068 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7685. Min Range: -2.7685
Max Act: 2.5277. Min Act: -0.1700
Data Index: 6210838 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7685. Min Range: -2.7685
Max Act: 2.5277. Min Act: -0.1700
Data Index: 4206296 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #19