Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 570 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.1785. Min Range: -3.1785
Max Act: 3.1785. Min Act: -0.1700
Data Index: 3484101 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1785. Min Range: -3.1785
Max Act: 3.0050. Min Act: -0.1700
Data Index: 2117152 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1785. Min Range: -3.1785
Max Act: 2.8784. Min Act: -0.1700
Data Index: 7431104 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1785. Min Range: -3.1785
Max Act: 2.8784. Min Act: -0.1700
Data Index: 4967506 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1785. Min Range: -3.1785
Max Act: 2.8625. Min Act: -0.1700
Data Index: 5812232 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1785. Min Range: -3.1785
Max Act: 2.8466. Min Act: -0.1700
Data Index: 5563330 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1785. Min Range: -3.1785
Max Act: 2.8466. Min Act: -0.1700
Data Index: 4951191 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1785. Min Range: -3.1785
Max Act: 2.8625. Min Act: -0.1700
Data Index: 1885724 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1785. Min Range: -3.1785
Max Act: 2.8307. Min Act: -0.1700
Data Index: 262571 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1785. Min Range: -3.1785
Max Act: 2.8148. Min Act: -0.1700
Data Index: 3700107 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1785. Min Range: -3.1785
Max Act: 2.8307. Min Act: -0.1700
Data Index: 335571 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1785. Min Range: -3.1785
Max Act: 2.8148. Min Act: -0.1700
Data Index: 6660642 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1785. Min Range: -3.1785
Max Act: 2.8148. Min Act: -0.1700
Data Index: 4991637 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1785. Min Range: -3.1785
Max Act: 2.7989. Min Act: -0.1700
Data Index: 4633357 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1785. Min Range: -3.1785
Max Act: 2.8148. Min Act: -0.1700
Data Index: 2624321 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1785. Min Range: -3.1785
Max Act: 2.7989. Min Act: -0.1700
Data Index: 2241878 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1785. Min Range: -3.1785
Max Act: 2.8148. Min Act: -0.1700
Data Index: 6750037 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1785. Min Range: -3.1785
Max Act: 2.7829. Min Act: -0.1700
Data Index: 2040476 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1785. Min Range: -3.1785
Max Act: 2.7829. Min Act: -0.1700
Data Index: 6736638 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1785. Min Range: -3.1785
Max Act: 2.7510. Min Act: -0.1700
Data Index: 3936161 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #19