Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5912 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7099. Min Range: -4.7099
Max Act: 4.7099. Min Act: -0.1700
Data Index: 7686627 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7099. Min Range: -4.7099
Max Act: 4.7099. Min Act: -0.1700
Data Index: 6456660 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7099. Min Range: -4.7099
Max Act: 4.5849. Min Act: -0.1700
Data Index: 553986 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7099. Min Range: -4.7099
Max Act: 4.5224. Min Act: -0.1700
Data Index: 8591143 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7099. Min Range: -4.7099
Max Act: 4.4912. Min Act: -0.1700
Data Index: 3759015 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7099. Min Range: -4.7099
Max Act: 4.4599. Min Act: -0.1700
Data Index: 307585 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7099. Min Range: -4.7099
Max Act: 4.4599. Min Act: -0.1700
Data Index: 6767958 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7099. Min Range: -4.7099
Max Act: 4.4599. Min Act: -0.1700
Data Index: 3959417 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7099. Min Range: -4.7099
Max Act: 4.4599. Min Act: -0.1700
Data Index: 2226557 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7099. Min Range: -4.7099
Max Act: 4.4599. Min Act: -0.1700
Data Index: 1848029 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7099. Min Range: -4.7099
Max Act: 4.4287. Min Act: -0.1700
Data Index: 553988 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7099. Min Range: -4.7099
Max Act: 4.4287. Min Act: -0.1700
Data Index: 7871638 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7099. Min Range: -4.7099
Max Act: 4.4287. Min Act: -0.1700
Data Index: 4624433 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7099. Min Range: -4.7099
Max Act: 4.3974. Min Act: -0.1700
Data Index: 3959421 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7099. Min Range: -4.7099
Max Act: 4.3974. Min Act: -0.1700
Data Index: 5372986 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7099. Min Range: -4.7099
Max Act: 4.3974. Min Act: -0.1700
Data Index: 4915294 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7099. Min Range: -4.7099
Max Act: 4.3974. Min Act: -0.1700
Data Index: 3959434 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7099. Min Range: -4.7099
Max Act: 4.3974. Min Act: -0.1700
Data Index: 1239798 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7099. Min Range: -4.7099
Max Act: 4.3974. Min Act: -0.1700
Data Index: 152852 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7099. Min Range: -4.7099
Max Act: 4.4287. Min Act: -0.1700
Data Index: 5919018 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #19