Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 18 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.3100. Min Range: -2.3100
Max Act: 2.3100. Min Act: -0.1700
Data Index: 1818860 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.3100. Min Range: -2.3100
Max Act: 2.2606. Min Act: -0.1700
Data Index: 7371253 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.3100. Min Range: -2.3100
Max Act: 2.2110. Min Act: -0.1700
Data Index: 5596910 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.3100. Min Range: -2.3100
Max Act: 2.1944. Min Act: -0.1700
Data Index: 7645063 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.3100. Min Range: -2.3100
Max Act: 2.1778. Min Act: -0.1700
Data Index: 7864464 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.3100. Min Range: -2.3100
Max Act: 2.1778. Min Act: -0.1700
Data Index: 2719585 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.3100. Min Range: -2.3100
Max Act: 2.1944. Min Act: -0.1700
Data Index: 6576277 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.3100. Min Range: -2.3100
Max Act: 2.1944. Min Act: -0.1700
Data Index: 1850578 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.3100. Min Range: -2.3100
Max Act: 2.1778. Min Act: -0.1700
Data Index: 1468633 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.3100. Min Range: -2.3100
Max Act: 2.1611. Min Act: -0.1700
Data Index: 5444576 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.3100. Min Range: -2.3100
Max Act: 2.1611. Min Act: -0.1700
Data Index: 4453776 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.3100. Min Range: -2.3100
Max Act: 2.1278. Min Act: -0.1700
Data Index: 6671683 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.3100. Min Range: -2.3100
Max Act: 2.1278. Min Act: -0.1700
Data Index: 2879293 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.3100. Min Range: -2.3100
Max Act: 2.1278. Min Act: -0.1700
Data Index: 4958078 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.3100. Min Range: -2.3100
Max Act: 2.1278. Min Act: -0.1700
Data Index: 758185 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.3100. Min Range: -2.3100
Max Act: 2.1444. Min Act: -0.1700
Data Index: 6323860 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.3100. Min Range: -2.3100
Max Act: 2.1444. Min Act: -0.1700
Data Index: 212514 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.3100. Min Range: -2.3100
Max Act: 2.1278. Min Act: -0.1700
Data Index: 983895 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.3100. Min Range: -2.3100
Max Act: 2.1444. Min Act: -0.1700
Data Index: 5553351 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.3100. Min Range: -2.3100
Max Act: 2.1444. Min Act: -0.1700
Data Index: 3245863 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #19