Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2468 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.4831. Min Range: -6.4831
Max Act: 6.4831. Min Act: -0.1700
Data Index: 2629597 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4831. Min Range: -6.4831
Max Act: 6.2644. Min Act: -0.1700
Data Index: 4312065 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4831. Min Range: -6.4831
Max Act: 6.2019. Min Act: -0.1700
Data Index: 1853528 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4831. Min Range: -6.4831
Max Act: 6.1394. Min Act: -0.1700
Data Index: 2327236 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4831. Min Range: -6.4831
Max Act: 6.1081. Min Act: -0.1700
Data Index: 1659429 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4831. Min Range: -6.4831
Max Act: 6.1394. Min Act: -0.1700
Data Index: 8548763 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4831. Min Range: -6.4831
Max Act: 6.1081. Min Act: -0.1700
Data Index: 3192694 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4831. Min Range: -6.4831
Max Act: 6.0456. Min Act: -0.1700
Data Index: 770584 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4831. Min Range: -6.4831
Max Act: 6.0144. Min Act: -0.1700
Data Index: 325531 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4831. Min Range: -6.4831
Max Act: 6.0456. Min Act: -0.1700
Data Index: 4594449 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4831. Min Range: -6.4831
Max Act: 6.0144. Min Act: -0.1700
Data Index: 1659430 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4831. Min Range: -6.4831
Max Act: 5.9831. Min Act: -0.1700
Data Index: 2896394 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4831. Min Range: -6.4831
Max Act: 5.9519. Min Act: -0.1700
Data Index: 601111 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4831. Min Range: -6.4831
Max Act: 5.9831. Min Act: -0.1700
Data Index: 8078213 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4831. Min Range: -6.4831
Max Act: 5.9206. Min Act: -0.1700
Data Index: 3263099 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4831. Min Range: -6.4831
Max Act: 5.9519. Min Act: -0.1700
Data Index: 4594448 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4831. Min Range: -6.4831
Max Act: 5.9206. Min Act: -0.1700
Data Index: 8560203 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4831. Min Range: -6.4831
Max Act: 5.8894. Min Act: -0.1700
Data Index: 7185856 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4831. Min Range: -6.4831
Max Act: 5.9206. Min Act: -0.1700
Data Index: 2182974 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4831. Min Range: -6.4831
Max Act: 5.8894. Min Act: -0.1700
Data Index: 7151232 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #19