Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4370 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2530. Min Range: -6.2530
Max Act: 6.2530. Min Act: -0.1700
Data Index: 3278742 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2530. Min Range: -6.2530
Max Act: 6.1280. Min Act: -0.1700
Data Index: 7883946 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2530. Min Range: -6.2530
Max Act: 6.1280. Min Act: -0.1700
Data Index: 4352740 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2530. Min Range: -6.2530
Max Act: 6.0342. Min Act: -0.1700
Data Index: 7770403 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2530. Min Range: -6.2530
Max Act: 6.0030. Min Act: -0.1700
Data Index: 7346021 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2530. Min Range: -6.2530
Max Act: 5.9405. Min Act: -0.1700
Data Index: 1525676 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2530. Min Range: -6.2530
Max Act: 5.9405. Min Act: -0.1700
Data Index: 5576972 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2530. Min Range: -6.2530
Max Act: 5.9405. Min Act: -0.1700
Data Index: 7294502 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2530. Min Range: -6.2530
Max Act: 5.9405. Min Act: -0.1700
Data Index: 6085933 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2530. Min Range: -6.2530
Max Act: 5.8780. Min Act: -0.1700
Data Index: 6348869 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2530. Min Range: -6.2530
Max Act: 5.9092. Min Act: -0.1700
Data Index: 3567038 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2530. Min Range: -6.2530
Max Act: 5.8467. Min Act: -0.1700
Data Index: 2997602 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2530. Min Range: -6.2530
Max Act: 5.8155. Min Act: -0.1700
Data Index: 3653318 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2530. Min Range: -6.2530
Max Act: 5.8780. Min Act: -0.1700
Data Index: 8586760 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2530. Min Range: -6.2530
Max Act: 5.8155. Min Act: -0.1700
Data Index: 5516711 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2530. Min Range: -6.2530
Max Act: 5.8155. Min Act: -0.1700
Data Index: 5798072 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2530. Min Range: -6.2530
Max Act: 5.8155. Min Act: -0.1700
Data Index: 167573 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2530. Min Range: -6.2530
Max Act: 5.7842. Min Act: -0.1700
Data Index: 5503829 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2530. Min Range: -6.2530
Max Act: 5.7842. Min Act: -0.1700
Data Index: 7526530 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2530. Min Range: -6.2530
Max Act: 5.7842. Min Act: -0.1700
Data Index: 577669 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #19