Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 27 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.0785. Min Range: -6.0785
Max Act: 6.0785. Min Act: -0.1700
Data Index: 861714 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0785. Min Range: -6.0785
Max Act: 6.0472. Min Act: -0.1700
Data Index: 7997277 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0785. Min Range: -6.0785
Max Act: 6.0472. Min Act: -0.1700
Data Index: 120370 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0785. Min Range: -6.0785
Max Act: 6.0160. Min Act: -0.1700
Data Index: 5358576 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0785. Min Range: -6.0785
Max Act: 6.0160. Min Act: -0.1700
Data Index: 1915492 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0785. Min Range: -6.0785
Max Act: 5.9847. Min Act: -0.1700
Data Index: 3908175 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0785. Min Range: -6.0785
Max Act: 5.9847. Min Act: -0.1700
Data Index: 3443097 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0785. Min Range: -6.0785
Max Act: 5.9535. Min Act: -0.1700
Data Index: 1238871 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0785. Min Range: -6.0785
Max Act: 5.9222. Min Act: -0.1700
Data Index: 1197777 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0785. Min Range: -6.0785
Max Act: 5.9222. Min Act: -0.1700
Data Index: 7481312 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0785. Min Range: -6.0785
Max Act: 5.8597. Min Act: -0.1700
Data Index: 5728114 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0785. Min Range: -6.0785
Max Act: 5.8597. Min Act: -0.1700
Data Index: 4784617 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0785. Min Range: -6.0785
Max Act: 5.8597. Min Act: -0.1700
Data Index: 807768 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0785. Min Range: -6.0785
Max Act: 5.8597. Min Act: -0.1700
Data Index: 1136962 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0785. Min Range: -6.0785
Max Act: 5.8597. Min Act: -0.1700
Data Index: 4735908 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0785. Min Range: -6.0785
Max Act: 5.8285. Min Act: -0.1700
Data Index: 5911331 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0785. Min Range: -6.0785
Max Act: 5.8285. Min Act: -0.1700
Data Index: 1421023 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0785. Min Range: -6.0785
Max Act: 5.7972. Min Act: -0.1700
Data Index: 5176692 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0785. Min Range: -6.0785
Max Act: 5.7972. Min Act: -0.1700
Data Index: 491702 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0785. Min Range: -6.0785
Max Act: 5.7660. Min Act: -0.1700
Data Index: 1840843 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #19