Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3055 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.2144. Min Range: -5.2144
Max Act: 5.2144. Min Act: -0.1700
Data Index: 5693775 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2144. Min Range: -5.2144
Max Act: 4.9644. Min Act: -0.1700
Data Index: 8442247 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2144. Min Range: -5.2144
Max Act: 4.9644. Min Act: -0.1700
Data Index: 5708236 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2144. Min Range: -5.2144
Max Act: 4.9331. Min Act: -0.1700
Data Index: 5713125 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2144. Min Range: -5.2144
Max Act: 4.9019. Min Act: -0.1700
Data Index: 2233821 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2144. Min Range: -5.2144
Max Act: 4.9019. Min Act: -0.1700
Data Index: 4629719 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2144. Min Range: -5.2144
Max Act: 4.8706. Min Act: -0.1700
Data Index: 4765794 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2144. Min Range: -5.2144
Max Act: 4.8394. Min Act: -0.1700
Data Index: 7548465 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2144. Min Range: -5.2144
Max Act: 4.8394. Min Act: -0.1700
Data Index: 7818907 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2144. Min Range: -5.2144
Max Act: 4.8394. Min Act: -0.1700
Data Index: 5273613 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2144. Min Range: -5.2144
Max Act: 4.8706. Min Act: -0.1700
Data Index: 5742362 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2144. Min Range: -5.2144
Max Act: 4.8394. Min Act: -0.1700
Data Index: 3800582 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2144. Min Range: -5.2144
Max Act: 4.8081. Min Act: -0.1700
Data Index: 1359558 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2144. Min Range: -5.2144
Max Act: 4.8081. Min Act: -0.1700
Data Index: 7095640 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2144. Min Range: -5.2144
Max Act: 4.8081. Min Act: -0.1700
Data Index: 8564866 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2144. Min Range: -5.2144
Max Act: 4.8081. Min Act: -0.1700
Data Index: 6703520 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2144. Min Range: -5.2144
Max Act: 4.8081. Min Act: -0.1700
Data Index: 5813339 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2144. Min Range: -5.2144
Max Act: 4.8081. Min Act: -0.1700
Data Index: 3438324 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2144. Min Range: -5.2144
Max Act: 4.7769. Min Act: -0.1700
Data Index: 2338338 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2144. Min Range: -5.2144
Max Act: 4.7456. Min Act: -0.1700
Data Index: 610483 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #19