Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2806 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8040. Min Range: -7.8040
Max Act: 7.8040. Min Act: -0.1700
Data Index: 1355390 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8040. Min Range: -7.8040
Max Act: 7.6790. Min Act: -0.1700
Data Index: 2709820 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8040. Min Range: -7.8040
Max Act: 7.3040. Min Act: -0.1700
Data Index: 2169294 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8040. Min Range: -7.8040
Max Act: 7.3040. Min Act: -0.1700
Data Index: 3228391 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8040. Min Range: -7.8040
Max Act: 7.1477. Min Act: -0.1700
Data Index: 1886407 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8040. Min Range: -7.8040
Max Act: 7.1165. Min Act: -0.1700
Data Index: 2655308 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8040. Min Range: -7.8040
Max Act: 7.0852. Min Act: -0.1700
Data Index: 1979427 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8040. Min Range: -7.8040
Max Act: 7.0227. Min Act: -0.1700
Data Index: 5064719 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8040. Min Range: -7.8040
Max Act: 7.0227. Min Act: -0.1700
Data Index: 2175402 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8040. Min Range: -7.8040
Max Act: 6.9915. Min Act: -0.1700
Data Index: 4272981 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8040. Min Range: -7.8040
Max Act: 6.8665. Min Act: -0.1700
Data Index: 2501925 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8040. Min Range: -7.8040
Max Act: 6.8352. Min Act: -0.1700
Data Index: 265942 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8040. Min Range: -7.8040
Max Act: 6.8040. Min Act: -0.1700
Data Index: 2722604 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8040. Min Range: -7.8040
Max Act: 6.8352. Min Act: -0.1700
Data Index: 2917422 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8040. Min Range: -7.8040
Max Act: 6.7727. Min Act: -0.1700
Data Index: 7269289 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8040. Min Range: -7.8040
Max Act: 6.7727. Min Act: -0.1700
Data Index: 713921 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8040. Min Range: -7.8040
Max Act: 6.7727. Min Act: -0.1700
Data Index: 3201830 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8040. Min Range: -7.8040
Max Act: 6.7727. Min Act: -0.1700
Data Index: 6643983 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8040. Min Range: -7.8040
Max Act: 6.7415. Min Act: -0.1700
Data Index: 4506250 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8040. Min Range: -7.8040
Max Act: 6.7415. Min Act: -0.1700
Data Index: 4925645 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #19