Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2783 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.8549. Min Range: -6.8549
Max Act: 6.8549. Min Act: -0.1700
Data Index: 6687352 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8549. Min Range: -6.8549
Max Act: 6.5736. Min Act: -0.1700
Data Index: 6845003 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8549. Min Range: -6.8549
Max Act: 6.5111. Min Act: -0.1700
Data Index: 4937608 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8549. Min Range: -6.8549
Max Act: 6.4799. Min Act: -0.1700
Data Index: 4145181 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8549. Min Range: -6.8549
Max Act: 6.4799. Min Act: -0.1700
Data Index: 1564460 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8549. Min Range: -6.8549
Max Act: 6.4174. Min Act: -0.1700
Data Index: 2747890 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8549. Min Range: -6.8549
Max Act: 6.3861. Min Act: -0.1700
Data Index: 5167392 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8549. Min Range: -6.8549
Max Act: 6.3549. Min Act: -0.1700
Data Index: 7749094 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8549. Min Range: -6.8549
Max Act: 6.4486. Min Act: -0.1700
Data Index: 7175923 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8549. Min Range: -6.8549
Max Act: 6.3549. Min Act: -0.1700
Data Index: 7428036 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8549. Min Range: -6.8549
Max Act: 6.3549. Min Act: -0.1700
Data Index: 1700156 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8549. Min Range: -6.8549
Max Act: 6.3236. Min Act: -0.1700
Data Index: 2722374 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8549. Min Range: -6.8549
Max Act: 6.2924. Min Act: -0.1700
Data Index: 8023867 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8549. Min Range: -6.8549
Max Act: 6.2924. Min Act: -0.1700
Data Index: 7489676 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8549. Min Range: -6.8549
Max Act: 6.2611. Min Act: -0.1700
Data Index: 4304646 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8549. Min Range: -6.8549
Max Act: 6.2924. Min Act: -0.1700
Data Index: 2826578 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8549. Min Range: -6.8549
Max Act: 6.2611. Min Act: -0.1700
Data Index: 8150770 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8549. Min Range: -6.8549
Max Act: 6.2611. Min Act: -0.1700
Data Index: 5934201 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8549. Min Range: -6.8549
Max Act: 6.2611. Min Act: -0.1700
Data Index: 115517 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8549. Min Range: -6.8549
Max Act: 6.2299. Min Act: -0.1700
Data Index: 269326 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #19