Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3329 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7498. Min Range: -6.7498
Max Act: 6.7498. Min Act: -0.1700
Data Index: 4287344 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7498. Min Range: -6.7498
Max Act: 6.7185. Min Act: -0.1700
Data Index: 8268541 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7498. Min Range: -6.7498
Max Act: 6.7185. Min Act: -0.1700
Data Index: 4512313 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7498. Min Range: -6.7498
Max Act: 6.6560. Min Act: -0.1700
Data Index: 8641019 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7498. Min Range: -6.7498
Max Act: 6.5935. Min Act: -0.1700
Data Index: 1512227 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7498. Min Range: -6.7498
Max Act: 6.5310. Min Act: -0.1700
Data Index: 2241710 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7498. Min Range: -6.7498
Max Act: 6.5623. Min Act: -0.1700
Data Index: 7435781 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7498. Min Range: -6.7498
Max Act: 6.5310. Min Act: -0.1700
Data Index: 6866958 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7498. Min Range: -6.7498
Max Act: 6.4998. Min Act: -0.1700
Data Index: 4327090 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7498. Min Range: -6.7498
Max Act: 6.4998. Min Act: -0.1700
Data Index: 2250666 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7498. Min Range: -6.7498
Max Act: 6.4373. Min Act: -0.1700
Data Index: 6303229 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7498. Min Range: -6.7498
Max Act: 6.4060. Min Act: -0.1700
Data Index: 3778520 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7498. Min Range: -6.7498
Max Act: 6.3748. Min Act: -0.1700
Data Index: 1309695 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7498. Min Range: -6.7498
Max Act: 6.3748. Min Act: -0.1700
Data Index: 8391843 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7498. Min Range: -6.7498
Max Act: 6.4060. Min Act: -0.1700
Data Index: 7165525 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7498. Min Range: -6.7498
Max Act: 6.3123. Min Act: -0.1700
Data Index: 4418749 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7498. Min Range: -6.7498
Max Act: 6.3123. Min Act: -0.1700
Data Index: 2976885 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7498. Min Range: -6.7498
Max Act: 6.2498. Min Act: -0.1700
Data Index: 4203899 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7498. Min Range: -6.7498
Max Act: 6.2498. Min Act: -0.1700
Data Index: 4225567 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7498. Min Range: -6.7498
Max Act: 6.2810. Min Act: -0.1700
Data Index: 7852455 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #19