Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1953 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.1612. Min Range: -3.1612
Max Act: 3.1612. Min Act: -0.1700
Data Index: 4295328 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1612. Min Range: -3.1612
Max Act: 3.0194. Min Act: -0.1700
Data Index: 8550425 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1612. Min Range: -3.1612
Max Act: 3.0509. Min Act: -0.1700
Data Index: 7484995 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1612. Min Range: -3.1612
Max Act: 2.9403. Min Act: -0.1700
Data Index: 7160363 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1612. Min Range: -3.1612
Max Act: 2.9086. Min Act: -0.1700
Data Index: 4272476 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1612. Min Range: -3.1612
Max Act: 2.9086. Min Act: -0.1700
Data Index: 2083290 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1612. Min Range: -3.1612
Max Act: 2.8769. Min Act: -0.1700
Data Index: 737651 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1612. Min Range: -3.1612
Max Act: 2.8769. Min Act: -0.1700
Data Index: 2632706 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1612. Min Range: -3.1612
Max Act: 2.8769. Min Act: -0.1700
Data Index: 2974035 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1612. Min Range: -3.1612
Max Act: 2.8769. Min Act: -0.1700
Data Index: 1685685 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1612. Min Range: -3.1612
Max Act: 2.8292. Min Act: -0.1700
Data Index: 7709098 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1612. Min Range: -3.1612
Max Act: 2.8769. Min Act: -0.1700
Data Index: 513069 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1612. Min Range: -3.1612
Max Act: 2.8292. Min Act: -0.1700
Data Index: 4657378 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1612. Min Range: -3.1612
Max Act: 2.8292. Min Act: -0.1700
Data Index: 4693918 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1612. Min Range: -3.1612
Max Act: 2.8133. Min Act: -0.1700
Data Index: 968084 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1612. Min Range: -3.1612
Max Act: 2.8133. Min Act: -0.1700
Data Index: 5686928 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1612. Min Range: -3.1612
Max Act: 2.7974. Min Act: -0.1700
Data Index: 6948842 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1612. Min Range: -3.1612
Max Act: 2.7974. Min Act: -0.1700
Data Index: 4435863 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1612. Min Range: -3.1612
Max Act: 2.7974. Min Act: -0.1700
Data Index: 5263844 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1612. Min Range: -3.1612
Max Act: 2.8133. Min Act: -0.1700
Data Index: 8076892 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #19