Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2637 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9796. Min Range: -5.9796
Max Act: 5.9796. Min Act: -0.1700
Data Index: 3763997 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9796. Min Range: -5.9796
Max Act: 5.9483. Min Act: -0.1700
Data Index: 1738033 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9796. Min Range: -5.9796
Max Act: 5.9171. Min Act: -0.1700
Data Index: 3517148 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9796. Min Range: -5.9796
Max Act: 5.9171. Min Act: -0.1700
Data Index: 440404 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9796. Min Range: -5.9796
Max Act: 5.8546. Min Act: -0.1700
Data Index: 7162782 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9796. Min Range: -5.9796
Max Act: 5.8546. Min Act: -0.1700
Data Index: 1876107 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9796. Min Range: -5.9796
Max Act: 5.8546. Min Act: -0.1700
Data Index: 1472265 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9796. Min Range: -5.9796
Max Act: 5.8546. Min Act: -0.1700
Data Index: 3773545 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9796. Min Range: -5.9796
Max Act: 5.7921. Min Act: -0.1700
Data Index: 2195645 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9796. Min Range: -5.9796
Max Act: 5.7921. Min Act: -0.1700
Data Index: 3884383 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9796. Min Range: -5.9796
Max Act: 5.7608. Min Act: -0.1700
Data Index: 5807210 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9796. Min Range: -5.9796
Max Act: 5.7608. Min Act: -0.1700
Data Index: 1738034 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9796. Min Range: -5.9796
Max Act: 5.7296. Min Act: -0.1700
Data Index: 4015545 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9796. Min Range: -5.9796
Max Act: 5.7608. Min Act: -0.1700
Data Index: 2211180 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9796. Min Range: -5.9796
Max Act: 5.6671. Min Act: -0.1700
Data Index: 8699848 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9796. Min Range: -5.9796
Max Act: 5.6983. Min Act: -0.1700
Data Index: 2594862 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9796. Min Range: -5.9796
Max Act: 5.7296. Min Act: -0.1700
Data Index: 4032636 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9796. Min Range: -5.9796
Max Act: 5.6671. Min Act: -0.1700
Data Index: 4556592 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9796. Min Range: -5.9796
Max Act: 5.6983. Min Act: -0.1700
Data Index: 4180350 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9796. Min Range: -5.9796
Max Act: 5.6671. Min Act: -0.1700
Data Index: 7157746 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #19