Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2529 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.6591. Min Range: -4.6591
Max Act: 4.6591. Min Act: -0.1700
Data Index: 6714123 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6591. Min Range: -4.6591
Max Act: 4.5028. Min Act: -0.1700
Data Index: 5190369 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6591. Min Range: -4.6591
Max Act: 4.4716. Min Act: -0.1700
Data Index: 4783373 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6591. Min Range: -4.6591
Max Act: 4.5028. Min Act: -0.1700
Data Index: 6932663 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6591. Min Range: -4.6591
Max Act: 4.4403. Min Act: -0.1700
Data Index: 8581075 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6591. Min Range: -4.6591
Max Act: 4.4403. Min Act: -0.1700
Data Index: 3340358 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6591. Min Range: -4.6591
Max Act: 4.3778. Min Act: -0.1700
Data Index: 362224 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6591. Min Range: -4.6591
Max Act: 4.3778. Min Act: -0.1700
Data Index: 362229 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6591. Min Range: -4.6591
Max Act: 4.3466. Min Act: -0.1700
Data Index: 5048865 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6591. Min Range: -4.6591
Max Act: 4.3466. Min Act: -0.1700
Data Index: 7473854 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6591. Min Range: -4.6591
Max Act: 4.3466. Min Act: -0.1700
Data Index: 7050071 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6591. Min Range: -4.6591
Max Act: 4.3153. Min Act: -0.1700
Data Index: 325211 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6591. Min Range: -4.6591
Max Act: 4.2841. Min Act: -0.1700
Data Index: 3432614 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6591. Min Range: -4.6591
Max Act: 4.2841. Min Act: -0.1700
Data Index: 2307667 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6591. Min Range: -4.6591
Max Act: 4.2528. Min Act: -0.1700
Data Index: 2536028 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6591. Min Range: -4.6591
Max Act: 4.2841. Min Act: -0.1700
Data Index: 2128849 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6591. Min Range: -4.6591
Max Act: 4.2528. Min Act: -0.1700
Data Index: 3062317 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6591. Min Range: -4.6591
Max Act: 4.2528. Min Act: -0.1700
Data Index: 6602532 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6591. Min Range: -4.6591
Max Act: 4.2528. Min Act: -0.1700
Data Index: 5947486 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6591. Min Range: -4.6591
Max Act: 4.2216. Min Act: -0.1700
Data Index: 3340360 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #19