Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6218 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.2917. Min Range: -4.2917
Max Act: 4.2917. Min Act: -0.1700
Data Index: 8637076 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2917. Min Range: -4.2917
Max Act: 4.1354. Min Act: -0.1700
Data Index: 6686224 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2917. Min Range: -4.2917
Max Act: 4.1042. Min Act: -0.1700
Data Index: 8354981 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2917. Min Range: -4.2917
Max Act: 4.1354. Min Act: -0.1700
Data Index: 5329487 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2917. Min Range: -4.2917
Max Act: 4.1042. Min Act: -0.1700
Data Index: 5696480 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2917. Min Range: -4.2917
Max Act: 4.0729. Min Act: -0.1700
Data Index: 456539 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2917. Min Range: -4.2917
Max Act: 4.1042. Min Act: -0.1700
Data Index: 1821082 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2917. Min Range: -4.2917
Max Act: 4.1042. Min Act: -0.1700
Data Index: 4890761 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2917. Min Range: -4.2917
Max Act: 4.0729. Min Act: -0.1700
Data Index: 4248025 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2917. Min Range: -4.2917
Max Act: 4.0417. Min Act: -0.1700
Data Index: 7680295 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2917. Min Range: -4.2917
Max Act: 4.0417. Min Act: -0.1700
Data Index: 2804394 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2917. Min Range: -4.2917
Max Act: 4.0417. Min Act: -0.1700
Data Index: 3254221 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2917. Min Range: -4.2917
Max Act: 4.0417. Min Act: -0.1700
Data Index: 3894455 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2917. Min Range: -4.2917
Max Act: 4.0417. Min Act: -0.1700
Data Index: 4526249 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2917. Min Range: -4.2917
Max Act: 4.0104. Min Act: -0.1700
Data Index: 1552460 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2917. Min Range: -4.2917
Max Act: 4.0104. Min Act: -0.1700
Data Index: 4140008 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2917. Min Range: -4.2917
Max Act: 4.0104. Min Act: -0.1700
Data Index: 7346279 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2917. Min Range: -4.2917
Max Act: 4.0104. Min Act: -0.1700
Data Index: 4499770 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2917. Min Range: -4.2917
Max Act: 3.9791. Min Act: -0.1700
Data Index: 6857825 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2917. Min Range: -4.2917
Max Act: 4.0104. Min Act: -0.1700
Data Index: 2608575 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #19