Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4797 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.3047. Min Range: -9.3047
Max Act: 9.3047. Min Act: -0.1700
Data Index: 1948213 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.3047. Min Range: -9.3047
Max Act: 9.1172. Min Act: -0.1700
Data Index: 3390680 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.3047. Min Range: -9.3047
Max Act: 9.1172. Min Act: -0.1700
Data Index: 8822111 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.3047. Min Range: -9.3047
Max Act: 8.9297. Min Act: -0.1700
Data Index: 3751355 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.3047. Min Range: -9.3047
Max Act: 8.9297. Min Act: -0.1700
Data Index: 1968763 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.3047. Min Range: -9.3047
Max Act: 8.8047. Min Act: -0.1700
Data Index: 2997625 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.3047. Min Range: -9.3047
Max Act: 8.8047. Min Act: -0.1700
Data Index: 5929165 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.3047. Min Range: -9.3047
Max Act: 8.7422. Min Act: -0.1700
Data Index: 2812026 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.3047. Min Range: -9.3047
Max Act: 8.6797. Min Act: -0.1700
Data Index: 6625484 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.3047. Min Range: -9.3047
Max Act: 8.6172. Min Act: -0.1700
Data Index: 3757930 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.3047. Min Range: -9.3047
Max Act: 8.6797. Min Act: -0.1700
Data Index: 8254779 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.3047. Min Range: -9.3047
Max Act: 8.6797. Min Act: -0.1700
Data Index: 8130000 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.3047. Min Range: -9.3047
Max Act: 8.6172. Min Act: -0.1700
Data Index: 8726896 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.3047. Min Range: -9.3047
Max Act: 8.6172. Min Act: -0.1700
Data Index: 1588374 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.3047. Min Range: -9.3047
Max Act: 8.6172. Min Act: -0.1700
Data Index: 5537268 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.3047. Min Range: -9.3047
Max Act: 8.6172. Min Act: -0.1700
Data Index: 6570551 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.3047. Min Range: -9.3047
Max Act: 8.5547. Min Act: -0.1700
Data Index: 4924944 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.3047. Min Range: -9.3047
Max Act: 8.5547. Min Act: -0.1700
Data Index: 8411578 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.3047. Min Range: -9.3047
Max Act: 8.4922. Min Act: -0.1700
Data Index: 2246317 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.3047. Min Range: -9.3047
Max Act: 8.4297. Min Act: -0.1700
Data Index: 2246313 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #19