Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2041 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.9611. Min Range: -2.9611
Max Act: 2.9611. Min Act: -0.1700
Data Index: 3760986 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9611. Min Range: -2.9611
Max Act: 2.9294. Min Act: -0.1700
Data Index: 6941236 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9611. Min Range: -2.9611
Max Act: 2.8977. Min Act: -0.1700
Data Index: 3588502 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9611. Min Range: -2.9611
Max Act: 2.9136. Min Act: -0.1700
Data Index: 3131934 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9611. Min Range: -2.9611
Max Act: 2.8977. Min Act: -0.1700
Data Index: 1725826 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9611. Min Range: -2.9611
Max Act: 2.9136. Min Act: -0.1700
Data Index: 2241412 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9611. Min Range: -2.9611
Max Act: 2.8977. Min Act: -0.1700
Data Index: 5321397 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9611. Min Range: -2.9611
Max Act: 2.8819. Min Act: -0.1700
Data Index: 1653497 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9611. Min Range: -2.9611
Max Act: 2.8660. Min Act: -0.1700
Data Index: 2085296 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9611. Min Range: -2.9611
Max Act: 2.8660. Min Act: -0.1700
Data Index: 6712329 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9611. Min Range: -2.9611
Max Act: 2.8819. Min Act: -0.1700
Data Index: 853935 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9611. Min Range: -2.9611
Max Act: 2.8660. Min Act: -0.1700
Data Index: 5330463 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9611. Min Range: -2.9611
Max Act: 2.8183. Min Act: -0.1700
Data Index: 700799 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9611. Min Range: -2.9611
Max Act: 2.8183. Min Act: -0.1700
Data Index: 4817813 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9611. Min Range: -2.9611
Max Act: 2.8183. Min Act: -0.1700
Data Index: 5550686 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9611. Min Range: -2.9611
Max Act: 2.8183. Min Act: -0.1700
Data Index: 3459128 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9611. Min Range: -2.9611
Max Act: 2.7865. Min Act: -0.1700
Data Index: 4266562 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9611. Min Range: -2.9611
Max Act: 2.7705. Min Act: -0.1700
Data Index: 8580552 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9611. Min Range: -2.9611
Max Act: 2.7865. Min Act: -0.1700
Data Index: 2283942 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9611. Min Range: -2.9611
Max Act: 2.7705. Min Act: -0.1700
Data Index: 106759 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #19