Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 979 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.8529. Min Range: -5.8529
Max Act: 5.8529. Min Act: -0.1700
Data Index: 2991793 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8529. Min Range: -5.8529
Max Act: 5.5716. Min Act: -0.1700
Data Index: 601698 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8529. Min Range: -5.8529
Max Act: 5.5091. Min Act: -0.1700
Data Index: 2852556 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8529. Min Range: -5.8529
Max Act: 5.4154. Min Act: -0.1700
Data Index: 4406436 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8529. Min Range: -5.8529
Max Act: 5.3841. Min Act: -0.1700
Data Index: 4071453 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8529. Min Range: -5.8529
Max Act: 5.3529. Min Act: -0.1700
Data Index: 2358607 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8529. Min Range: -5.8529
Max Act: 5.3529. Min Act: -0.1700
Data Index: 2803891 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8529. Min Range: -5.8529
Max Act: 5.3529. Min Act: -0.1700
Data Index: 8264351 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8529. Min Range: -5.8529
Max Act: 5.3216. Min Act: -0.1700
Data Index: 1031707 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8529. Min Range: -5.8529
Max Act: 5.3529. Min Act: -0.1700
Data Index: 6916870 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8529. Min Range: -5.8529
Max Act: 5.2904. Min Act: -0.1700
Data Index: 534264 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8529. Min Range: -5.8529
Max Act: 5.2904. Min Act: -0.1700
Data Index: 4928808 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8529. Min Range: -5.8529
Max Act: 5.2904. Min Act: -0.1700
Data Index: 1061460 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8529. Min Range: -5.8529
Max Act: 5.3216. Min Act: -0.1700
Data Index: 1781321 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8529. Min Range: -5.8529
Max Act: 5.2904. Min Act: -0.1700
Data Index: 6927870 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8529. Min Range: -5.8529
Max Act: 5.2904. Min Act: -0.1700
Data Index: 1438089 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8529. Min Range: -5.8529
Max Act: 5.2904. Min Act: -0.1700
Data Index: 2764587 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8529. Min Range: -5.8529
Max Act: 5.2591. Min Act: -0.1700
Data Index: 7631572 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8529. Min Range: -5.8529
Max Act: 5.2904. Min Act: -0.1700
Data Index: 6321149 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8529. Min Range: -5.8529
Max Act: 5.2591. Min Act: -0.1700
Data Index: 2543507 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #19