Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2616 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6173. Min Range: -7.6173
Max Act: 7.6173. Min Act: -0.1700
Data Index: 3050424 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6173. Min Range: -7.6173
Max Act: 7.5861. Min Act: -0.1700
Data Index: 7969364 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6173. Min Range: -7.6173
Max Act: 7.4611. Min Act: -0.1700
Data Index: 1335664 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6173. Min Range: -7.6173
Max Act: 7.3986. Min Act: -0.1700
Data Index: 3330397 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6173. Min Range: -7.6173
Max Act: 7.3673. Min Act: -0.1700
Data Index: 1603970 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6173. Min Range: -7.6173
Max Act: 7.3048. Min Act: -0.1700
Data Index: 6318066 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6173. Min Range: -7.6173
Max Act: 7.3048. Min Act: -0.1700
Data Index: 2408669 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6173. Min Range: -7.6173
Max Act: 7.2736. Min Act: -0.1700
Data Index: 5784986 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6173. Min Range: -7.6173
Max Act: 7.2111. Min Act: -0.1700
Data Index: 2347120 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6173. Min Range: -7.6173
Max Act: 7.2111. Min Act: -0.1700
Data Index: 2698136 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6173. Min Range: -7.6173
Max Act: 7.1486. Min Act: -0.1700
Data Index: 2169193 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6173. Min Range: -7.6173
Max Act: 7.1173. Min Act: -0.1700
Data Index: 588255 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6173. Min Range: -7.6173
Max Act: 7.1173. Min Act: -0.1700
Data Index: 5427890 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6173. Min Range: -7.6173
Max Act: 7.1173. Min Act: -0.1700
Data Index: 861329 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6173. Min Range: -7.6173
Max Act: 7.0861. Min Act: -0.1700
Data Index: 366464 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6173. Min Range: -7.6173
Max Act: 7.1173. Min Act: -0.1700
Data Index: 5047486 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6173. Min Range: -7.6173
Max Act: 7.0861. Min Act: -0.1700
Data Index: 5097603 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6173. Min Range: -7.6173
Max Act: 7.0548. Min Act: -0.1700
Data Index: 2831652 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6173. Min Range: -7.6173
Max Act: 7.0548. Min Act: -0.1700
Data Index: 1683291 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6173. Min Range: -7.6173
Max Act: 7.0548. Min Act: -0.1700
Data Index: 545730 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #19