Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3068 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1200. Min Range: -5.1200
Max Act: 5.1200. Min Act: -0.1700
Data Index: 5990174 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1200. Min Range: -5.1200
Max Act: 5.0887. Min Act: -0.1700
Data Index: 3659180 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1200. Min Range: -5.1200
Max Act: 5.0262. Min Act: -0.1700
Data Index: 1587821 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1200. Min Range: -5.1200
Max Act: 5.0262. Min Act: -0.1700
Data Index: 4609616 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1200. Min Range: -5.1200
Max Act: 5.0262. Min Act: -0.1700
Data Index: 3529843 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1200. Min Range: -5.1200
Max Act: 4.9950. Min Act: -0.1700
Data Index: 5225077 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1200. Min Range: -5.1200
Max Act: 4.9950. Min Act: -0.1700
Data Index: 2337184 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1200. Min Range: -5.1200
Max Act: 4.9637. Min Act: -0.1700
Data Index: 7765431 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1200. Min Range: -5.1200
Max Act: 4.9637. Min Act: -0.1700
Data Index: 5812983 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1200. Min Range: -5.1200
Max Act: 4.9637. Min Act: -0.1700
Data Index: 5275915 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1200. Min Range: -5.1200
Max Act: 4.9637. Min Act: -0.1700
Data Index: 7519289 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1200. Min Range: -5.1200
Max Act: 4.9325. Min Act: -0.1700
Data Index: 5238125 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1200. Min Range: -5.1200
Max Act: 4.9325. Min Act: -0.1700
Data Index: 3623467 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1200. Min Range: -5.1200
Max Act: 4.9012. Min Act: -0.1700
Data Index: 1991514 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1200. Min Range: -5.1200
Max Act: 4.9012. Min Act: -0.1700
Data Index: 7515405 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1200. Min Range: -5.1200
Max Act: 4.9012. Min Act: -0.1700
Data Index: 3099919 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1200. Min Range: -5.1200
Max Act: 4.9012. Min Act: -0.1700
Data Index: 7207032 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1200. Min Range: -5.1200
Max Act: 4.9012. Min Act: -0.1700
Data Index: 5543445 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1200. Min Range: -5.1200
Max Act: 4.8700. Min Act: -0.1700
Data Index: 1115109 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1200. Min Range: -5.1200
Max Act: 4.8700. Min Act: -0.1700
Data Index: 2971284 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #19