Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 272 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.4419. Min Range: -2.4419
Max Act: 2.4419. Min Act: -0.1700
Data Index: 6681480 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.4419. Min Range: -2.4419
Max Act: 2.4419. Min Act: -0.1700
Data Index: 3404793 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.4419. Min Range: -2.4419
Max Act: 2.3111. Min Act: -0.1700
Data Index: 4997654 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.4419. Min Range: -2.4419
Max Act: 2.2782. Min Act: -0.1700
Data Index: 5119211 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.4419. Min Range: -2.4419
Max Act: 2.2617. Min Act: -0.1700
Data Index: 4066166 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.4419. Min Range: -2.4419
Max Act: 2.2452. Min Act: -0.1700
Data Index: 6139911 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.4419. Min Range: -2.4419
Max Act: 2.2617. Min Act: -0.1700
Data Index: 2976710 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.4419. Min Range: -2.4419
Max Act: 2.2452. Min Act: -0.1700
Data Index: 3218831 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.4419. Min Range: -2.4419
Max Act: 2.2287. Min Act: -0.1700
Data Index: 8797529 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.4419. Min Range: -2.4419
Max Act: 2.2121. Min Act: -0.1700
Data Index: 2596318 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.4419. Min Range: -2.4419
Max Act: 2.1955. Min Act: -0.1700
Data Index: 6077150 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.4419. Min Range: -2.4419
Max Act: 2.1955. Min Act: -0.1700
Data Index: 7725425 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.4419. Min Range: -2.4419
Max Act: 2.1955. Min Act: -0.1700
Data Index: 3701090 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.4419. Min Range: -2.4419
Max Act: 2.1622. Min Act: -0.1700
Data Index: 2693640 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.4419. Min Range: -2.4419
Max Act: 2.1955. Min Act: -0.1700
Data Index: 3307078 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.4419. Min Range: -2.4419
Max Act: 2.1622. Min Act: -0.1700
Data Index: 5161770 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.4419. Min Range: -2.4419
Max Act: 2.1622. Min Act: -0.1700
Data Index: 6681481 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.4419. Min Range: -2.4419
Max Act: 2.1622. Min Act: -0.1700
Data Index: 3269520 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.4419. Min Range: -2.4419
Max Act: 2.1622. Min Act: -0.1700
Data Index: 7098222 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.4419. Min Range: -2.4419
Max Act: 2.1622. Min Act: -0.1700
Data Index: 38610 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #19