Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4442 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.6028. Min Range: -10.6028
Max Act: 10.6028. Min Act: -0.1700
Data Index: 6830043 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.6028. Min Range: -10.6028
Max Act: 9.9153. Min Act: -0.1700
Data Index: 4649151 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.6028. Min Range: -10.6028
Max Act: 9.6028. Min Act: -0.1700
Data Index: 3701353 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.6028. Min Range: -10.6028
Max Act: 9.4778. Min Act: -0.1700
Data Index: 3725939 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.6028. Min Range: -10.6028
Max Act: 9.4778. Min Act: -0.1700
Data Index: 1348822 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.6028. Min Range: -10.6028
Max Act: 9.4778. Min Act: -0.1700
Data Index: 6463725 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.6028. Min Range: -10.6028
Max Act: 9.4153. Min Act: -0.1700
Data Index: 3992988 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.6028. Min Range: -10.6028
Max Act: 9.4153. Min Act: -0.1700
Data Index: 922849 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.6028. Min Range: -10.6028
Max Act: 9.4153. Min Act: -0.1700
Data Index: 6182217 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.6028. Min Range: -10.6028
Max Act: 9.4153. Min Act: -0.1700
Data Index: 1088649 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.6028. Min Range: -10.6028
Max Act: 9.3528. Min Act: -0.1700
Data Index: 8449653 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.6028. Min Range: -10.6028
Max Act: 9.2903. Min Act: -0.1700
Data Index: 6862846 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.6028. Min Range: -10.6028
Max Act: 9.3528. Min Act: -0.1700
Data Index: 3918995 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.6028. Min Range: -10.6028
Max Act: 9.3528. Min Act: -0.1700
Data Index: 5784005 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.6028. Min Range: -10.6028
Max Act: 9.2903. Min Act: -0.1700
Data Index: 4075241 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.6028. Min Range: -10.6028
Max Act: 9.2903. Min Act: -0.1700
Data Index: 3961351 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.6028. Min Range: -10.6028
Max Act: 9.2278. Min Act: -0.1700
Data Index: 697937 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.6028. Min Range: -10.6028
Max Act: 9.1653. Min Act: -0.1700
Data Index: 5178745 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.6028. Min Range: -10.6028
Max Act: 9.2278. Min Act: -0.1700
Data Index: 3340204 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.6028. Min Range: -10.6028
Max Act: 9.2278. Min Act: -0.1700
Data Index: 5593772 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #19