Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2791 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.2196. Min Range: -5.2196
Max Act: 5.2196. Min Act: -0.1700
Data Index: 2358111 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2196. Min Range: -5.2196
Max Act: 5.1883. Min Act: -0.1700
Data Index: 4273599 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2196. Min Range: -5.2196
Max Act: 5.1258. Min Act: -0.1700
Data Index: 3682898 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2196. Min Range: -5.2196
Max Act: 5.1258. Min Act: -0.1700
Data Index: 1939860 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2196. Min Range: -5.2196
Max Act: 5.0946. Min Act: -0.1700
Data Index: 4635897 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2196. Min Range: -5.2196
Max Act: 5.1258. Min Act: -0.1700
Data Index: 5435424 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2196. Min Range: -5.2196
Max Act: 5.0946. Min Act: -0.1700
Data Index: 908825 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2196. Min Range: -5.2196
Max Act: 5.0633. Min Act: -0.1700
Data Index: 5487743 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2196. Min Range: -5.2196
Max Act: 5.0946. Min Act: -0.1700
Data Index: 8580018 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2196. Min Range: -5.2196
Max Act: 5.0633. Min Act: -0.1700
Data Index: 899473 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2196. Min Range: -5.2196
Max Act: 5.0633. Min Act: -0.1700
Data Index: 5814657 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2196. Min Range: -5.2196
Max Act: 5.0321. Min Act: -0.1700
Data Index: 4541928 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2196. Min Range: -5.2196
Max Act: 5.0633. Min Act: -0.1700
Data Index: 7199427 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2196. Min Range: -5.2196
Max Act: 5.0321. Min Act: -0.1700
Data Index: 6275291 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2196. Min Range: -5.2196
Max Act: 5.0633. Min Act: -0.1700
Data Index: 7490633 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2196. Min Range: -5.2196
Max Act: 5.0008. Min Act: -0.1700
Data Index: 244004 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2196. Min Range: -5.2196
Max Act: 5.0008. Min Act: -0.1700
Data Index: 5226562 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2196. Min Range: -5.2196
Max Act: 4.9696. Min Act: -0.1700
Data Index: 8586429 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2196. Min Range: -5.2196
Max Act: 5.0008. Min Act: -0.1700
Data Index: 5458310 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2196. Min Range: -5.2196
Max Act: 4.9696. Min Act: -0.1700
Data Index: 4004416 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #19