Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2694 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.2527. Min Range: -4.2527
Max Act: 4.2527. Min Act: -0.1700
Data Index: 1425222 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2527. Min Range: -4.2527
Max Act: 4.1589. Min Act: -0.1700
Data Index: 8585706 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2527. Min Range: -4.2527
Max Act: 4.1902. Min Act: -0.1700
Data Index: 3825996 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2527. Min Range: -4.2527
Max Act: 4.0964. Min Act: -0.1700
Data Index: 3643955 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2527. Min Range: -4.2527
Max Act: 4.0652. Min Act: -0.1700
Data Index: 8717192 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2527. Min Range: -4.2527
Max Act: 4.0652. Min Act: -0.1700
Data Index: 6688757 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2527. Min Range: -4.2527
Max Act: 4.0652. Min Act: -0.1700
Data Index: 4584550 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2527. Min Range: -4.2527
Max Act: 4.0652. Min Act: -0.1700
Data Index: 3863196 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2527. Min Range: -4.2527
Max Act: 4.0339. Min Act: -0.1700
Data Index: 3063607 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2527. Min Range: -4.2527
Max Act: 4.0339. Min Act: -0.1700
Data Index: 2252936 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2527. Min Range: -4.2527
Max Act: 4.0026. Min Act: -0.1700
Data Index: 359464 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2527. Min Range: -4.2527
Max Act: 4.0026. Min Act: -0.1700
Data Index: 917302 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2527. Min Range: -4.2527
Max Act: 4.0026. Min Act: -0.1700
Data Index: 4585039 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2527. Min Range: -4.2527
Max Act: 3.9714. Min Act: -0.1700
Data Index: 1976354 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2527. Min Range: -4.2527
Max Act: 3.9714. Min Act: -0.1700
Data Index: 708280 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2527. Min Range: -4.2527
Max Act: 3.9401. Min Act: -0.1700
Data Index: 3880740 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2527. Min Range: -4.2527
Max Act: 3.9089. Min Act: -0.1700
Data Index: 2445913 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2527. Min Range: -4.2527
Max Act: 3.8776. Min Act: -0.1700
Data Index: 5729642 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2527. Min Range: -4.2527
Max Act: 3.9089. Min Act: -0.1700
Data Index: 8190260 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2527. Min Range: -4.2527
Max Act: 3.9089. Min Act: -0.1700
Data Index: 7083934 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #19