Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2087 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.2733. Min Range: -4.2733
Max Act: 4.2420. Min Act: -0.1700
Data Index: 4562183 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2733. Min Range: -4.2733
Max Act: 4.2733. Min Act: -0.1700
Data Index: 7695547 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2733. Min Range: -4.2733
Max Act: 4.1170. Min Act: -0.1700
Data Index: 6196843 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2733. Min Range: -4.2733
Max Act: 4.1170. Min Act: -0.1700
Data Index: 2602694 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2733. Min Range: -4.2733
Max Act: 4.1170. Min Act: -0.1700
Data Index: 6936410 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2733. Min Range: -4.2733
Max Act: 4.1170. Min Act: -0.1700
Data Index: 2270912 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2733. Min Range: -4.2733
Max Act: 4.1170. Min Act: -0.1699
Data Index: 7377522 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2733. Min Range: -4.2733
Max Act: 4.1170. Min Act: -0.1700
Data Index: 5899224 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2733. Min Range: -4.2733
Max Act: 4.0857. Min Act: -0.1700
Data Index: 6095322 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2733. Min Range: -4.2733
Max Act: 4.0857. Min Act: -0.1700
Data Index: 222957 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2733. Min Range: -4.2733
Max Act: 4.0545. Min Act: -0.1700
Data Index: 2747625 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2733. Min Range: -4.2733
Max Act: 4.0545. Min Act: -0.1700
Data Index: 4446433 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2733. Min Range: -4.2733
Max Act: 4.0545. Min Act: -0.1700
Data Index: 1755724 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2733. Min Range: -4.2733
Max Act: 4.0545. Min Act: -0.1700
Data Index: 6062648 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2733. Min Range: -4.2733
Max Act: 4.0232. Min Act: -0.1700
Data Index: 7445635 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2733. Min Range: -4.2733
Max Act: 4.0232. Min Act: -0.1700
Data Index: 7800914 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2733. Min Range: -4.2733
Max Act: 3.9607. Min Act: -0.1700
Data Index: 7074229 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2733. Min Range: -4.2733
Max Act: 3.9294. Min Act: -0.1700
Data Index: 8299802 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2733. Min Range: -4.2733
Max Act: 3.9294. Min Act: -0.1700
Data Index: 1576289 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2733. Min Range: -4.2733
Max Act: 3.9607. Min Act: -0.1700
Data Index: 3771318 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #19