Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 454 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.4659. Min Range: -3.4659
Max Act: 3.4659. Min Act: -0.1700
Data Index: 8075631 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4659. Min Range: -3.4659
Max Act: 3.4345. Min Act: -0.1700
Data Index: 8340636 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4659. Min Range: -3.4659
Max Act: 3.4345. Min Act: -0.1700
Data Index: 279929 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4659. Min Range: -3.4659
Max Act: 3.4345. Min Act: -0.1700
Data Index: 8169223 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4659. Min Range: -3.4659
Max Act: 3.4345. Min Act: -0.1700
Data Index: 8026973 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4659. Min Range: -3.4659
Max Act: 3.4345. Min Act: -0.1700
Data Index: 6285206 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4659. Min Range: -3.4659
Max Act: 3.4032. Min Act: -0.1700
Data Index: 964112 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4659. Min Range: -3.4659
Max Act: 3.3718. Min Act: -0.1700
Data Index: 6607801 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4659. Min Range: -3.4659
Max Act: 3.4032. Min Act: -0.1700
Data Index: 1703485 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4659. Min Range: -3.4659
Max Act: 3.4032. Min Act: -0.1700
Data Index: 5586906 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4659. Min Range: -3.4659
Max Act: 3.4032. Min Act: -0.1700
Data Index: 1582188 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4659. Min Range: -3.4659
Max Act: 3.4032. Min Act: -0.1700
Data Index: 4260289 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4659. Min Range: -3.4659
Max Act: 3.4032. Min Act: -0.1700
Data Index: 4088194 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4659. Min Range: -3.4659
Max Act: 3.4032. Min Act: -0.1700
Data Index: 3944278 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4659. Min Range: -3.4659
Max Act: 3.4032. Min Act: -0.1700
Data Index: 3612969 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4659. Min Range: -3.4659
Max Act: 3.3718. Min Act: -0.1700
Data Index: 3451349 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4659. Min Range: -3.4659
Max Act: 3.4032. Min Act: -0.1700
Data Index: 3185676 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4659. Min Range: -3.4659
Max Act: 3.3718. Min Act: -0.1700
Data Index: 2427774 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4659. Min Range: -3.4659
Max Act: 3.3718. Min Act: -0.1700
Data Index: 2461699 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4659. Min Range: -3.4659
Max Act: 3.3718. Min Act: -0.1700
Data Index: 2646202 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #19