Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2195 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.2787. Min Range: -7.2787
Max Act: 7.2787. Min Act: -0.1700
Data Index: 1406742 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2787. Min Range: -7.2787
Max Act: 7.1225. Min Act: -0.1700
Data Index: 8818940 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2787. Min Range: -7.2787
Max Act: 7.1537. Min Act: -0.1700
Data Index: 8818942 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2787. Min Range: -7.2787
Max Act: 7.0912. Min Act: -0.1700
Data Index: 6003726 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2787. Min Range: -7.2787
Max Act: 7.0600. Min Act: -0.1700
Data Index: 8818922 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2787. Min Range: -7.2787
Max Act: 7.0287. Min Act: -0.1700
Data Index: 7819989 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2787. Min Range: -7.2787
Max Act: 7.0287. Min Act: -0.1700
Data Index: 5560026 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2787. Min Range: -7.2787
Max Act: 7.0600. Min Act: -0.1700
Data Index: 7871253 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2787. Min Range: -7.2787
Max Act: 7.0287. Min Act: -0.1700
Data Index: 4790657 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2787. Min Range: -7.2787
Max Act: 7.0287. Min Act: -0.1700
Data Index: 4599564 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2787. Min Range: -7.2787
Max Act: 6.9975. Min Act: -0.1700
Data Index: 4599576 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2787. Min Range: -7.2787
Max Act: 6.9975. Min Act: -0.1700
Data Index: 5693122 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2787. Min Range: -7.2787
Max Act: 6.9975. Min Act: -0.1700
Data Index: 1955122 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2787. Min Range: -7.2787
Max Act: 6.9662. Min Act: -0.1700
Data Index: 8818920 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2787. Min Range: -7.2787
Max Act: 6.9350. Min Act: -0.1700
Data Index: 6190944 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2787. Min Range: -7.2787
Max Act: 6.9037. Min Act: -0.1700
Data Index: 6374108 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2787. Min Range: -7.2787
Max Act: 6.8725. Min Act: -0.1700
Data Index: 7871276 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2787. Min Range: -7.2787
Max Act: 6.8725. Min Act: -0.1700
Data Index: 2745419 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2787. Min Range: -7.2787
Max Act: 6.9037. Min Act: -0.1700
Data Index: 8555405 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2787. Min Range: -7.2787
Max Act: 6.8725. Min Act: -0.1700
Data Index: 8627674 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #19