Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3253 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.8654. Min Range: -3.8654
Max Act: 3.8654. Min Act: -0.1700
Data Index: 814415 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8654. Min Range: -3.8654
Max Act: 3.8029. Min Act: -0.1700
Data Index: 3780467 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8654. Min Range: -3.8654
Max Act: 3.7716. Min Act: -0.1700
Data Index: 2563984 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8654. Min Range: -3.8654
Max Act: 3.6778. Min Act: -0.1700
Data Index: 8193394 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8654. Min Range: -3.8654
Max Act: 3.6308. Min Act: -0.1700
Data Index: 4022779 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8654. Min Range: -3.8654
Max Act: 3.5526. Min Act: -0.1700
Data Index: 62659 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8654. Min Range: -3.8654
Max Act: 3.5839. Min Act: -0.1700
Data Index: 2563983 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8654. Min Range: -3.8654
Max Act: 3.5526. Min Act: -0.1700
Data Index: 254114 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8654. Min Range: -3.8654
Max Act: 3.5526. Min Act: -0.1700
Data Index: 2504167 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8654. Min Range: -3.8654
Max Act: 3.5056. Min Act: -0.1700
Data Index: 1897762 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8654. Min Range: -3.8654
Max Act: 3.5056. Min Act: -0.1700
Data Index: 2681572 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8654. Min Range: -3.8654
Max Act: 3.5369. Min Act: -0.1700
Data Index: 994805 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8654. Min Range: -3.8654
Max Act: 3.4899. Min Act: -0.1700
Data Index: 3805590 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8654. Min Range: -3.8654
Max Act: 3.4899. Min Act: -0.1700
Data Index: 7174237 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8654. Min Range: -3.8654
Max Act: 3.4899. Min Act: -0.1700
Data Index: 2681571 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8654. Min Range: -3.8654
Max Act: 3.4429. Min Act: -0.1700
Data Index: 4278922 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8654. Min Range: -3.8654
Max Act: 3.4586. Min Act: -0.1700
Data Index: 8447152 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8654. Min Range: -3.8654
Max Act: 3.4273. Min Act: -0.1700
Data Index: 1368357 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8654. Min Range: -3.8654
Max Act: 3.4586. Min Act: -0.1700
Data Index: 698124 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8654. Min Range: -3.8654
Max Act: 3.4116. Min Act: -0.1700
Data Index: 6203308 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #19