Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2423 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.8975. Min Range: -4.8975
Max Act: 4.8975. Min Act: -0.1700
Data Index: 3341471 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8975. Min Range: -4.8975
Max Act: 4.8037. Min Act: -0.1700
Data Index: 5986031 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8975. Min Range: -4.8975
Max Act: 4.7100. Min Act: -0.1700
Data Index: 1168623 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8975. Min Range: -4.8975
Max Act: 4.6475. Min Act: -0.1700
Data Index: 587418 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8975. Min Range: -4.8975
Max Act: 4.6162. Min Act: -0.1700
Data Index: 1580427 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8975. Min Range: -4.8975
Max Act: 4.6162. Min Act: -0.1700
Data Index: 253803 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8975. Min Range: -4.8975
Max Act: 4.5850. Min Act: -0.1700
Data Index: 3329917 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8975. Min Range: -4.8975
Max Act: 4.5850. Min Act: -0.1700
Data Index: 1669251 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8975. Min Range: -4.8975
Max Act: 4.5850. Min Act: -0.1700
Data Index: 6105205 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8975. Min Range: -4.8975
Max Act: 4.5850. Min Act: -0.1700
Data Index: 4328181 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8975. Min Range: -4.8975
Max Act: 4.5537. Min Act: -0.1700
Data Index: 4324943 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8975. Min Range: -4.8975
Max Act: 4.5225. Min Act: -0.1700
Data Index: 1364959 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8975. Min Range: -4.8975
Max Act: 4.5225. Min Act: -0.1700
Data Index: 5436839 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8975. Min Range: -4.8975
Max Act: 4.5225. Min Act: -0.1700
Data Index: 8548439 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8975. Min Range: -4.8975
Max Act: 4.4912. Min Act: -0.1700
Data Index: 4834096 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8975. Min Range: -4.8975
Max Act: 4.4912. Min Act: -0.1700
Data Index: 519369 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8975. Min Range: -4.8975
Max Act: 4.4600. Min Act: -0.1700
Data Index: 1364961 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8975. Min Range: -4.8975
Max Act: 4.4912. Min Act: -0.1700
Data Index: 1213460 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8975. Min Range: -4.8975
Max Act: 4.4600. Min Act: -0.1700
Data Index: 4738000 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8975. Min Range: -4.8975
Max Act: 4.4287. Min Act: -0.1700
Data Index: 6569329 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #19