Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1032 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.9142. Min Range: -5.9142
Max Act: 5.9142. Min Act: -0.1700
Data Index: 1809166 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9142. Min Range: -5.9142
Max Act: 5.7892. Min Act: -0.1700
Data Index: 3332176 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9142. Min Range: -5.9142
Max Act: 5.7579. Min Act: -0.1700
Data Index: 8320406 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9142. Min Range: -5.9142
Max Act: 5.6954. Min Act: -0.1700
Data Index: 2323083 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9142. Min Range: -5.9142
Max Act: 5.6329. Min Act: -0.1700
Data Index: 5967319 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9142. Min Range: -5.9142
Max Act: 5.5704. Min Act: -0.1700
Data Index: 488191 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9142. Min Range: -5.9142
Max Act: 5.6017. Min Act: -0.1700
Data Index: 5821210 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9142. Min Range: -5.9142
Max Act: 5.5704. Min Act: -0.1700
Data Index: 7829447 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9142. Min Range: -5.9142
Max Act: 5.5392. Min Act: -0.1700
Data Index: 6184131 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9142. Min Range: -5.9142
Max Act: 5.5079. Min Act: -0.1700
Data Index: 807270 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9142. Min Range: -5.9142
Max Act: 5.5079. Min Act: -0.1700
Data Index: 5694271 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9142. Min Range: -5.9142
Max Act: 5.4454. Min Act: -0.1700
Data Index: 1891028 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9142. Min Range: -5.9142
Max Act: 5.4767. Min Act: -0.1700
Data Index: 809206 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9142. Min Range: -5.9142
Max Act: 5.4767. Min Act: -0.1700
Data Index: 2216332 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9142. Min Range: -5.9142
Max Act: 5.4454. Min Act: -0.1700
Data Index: 7522931 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9142. Min Range: -5.9142
Max Act: 5.4454. Min Act: -0.1700
Data Index: 382901 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9142. Min Range: -5.9142
Max Act: 5.3829. Min Act: -0.1700
Data Index: 5312042 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9142. Min Range: -5.9142
Max Act: 5.3829. Min Act: -0.1700
Data Index: 2345838 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9142. Min Range: -5.9142
Max Act: 5.3517. Min Act: -0.1700
Data Index: 2255253 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9142. Min Range: -5.9142
Max Act: 5.3204. Min Act: -0.1700
Data Index: 5197683 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #19