Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6250 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3602. Min Range: -6.3602
Max Act: 6.3602. Min Act: -0.1700
Data Index: 2346923 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3602. Min Range: -6.3602
Max Act: 6.3602. Min Act: -0.1700
Data Index: 5292839 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3602. Min Range: -6.3602
Max Act: 6.2664. Min Act: -0.1700
Data Index: 233042 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3602. Min Range: -6.3602
Max Act: 6.2664. Min Act: -0.1700
Data Index: 6469038 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3602. Min Range: -6.3602
Max Act: 6.2352. Min Act: -0.1700
Data Index: 5517747 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3602. Min Range: -6.3602
Max Act: 6.2039. Min Act: -0.1700
Data Index: 5891706 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3602. Min Range: -6.3602
Max Act: 6.1414. Min Act: -0.1700
Data Index: 2720277 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3602. Min Range: -6.3602
Max Act: 6.0164. Min Act: -0.1700
Data Index: 5512621 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3602. Min Range: -6.3602
Max Act: 6.0477. Min Act: -0.1700
Data Index: 7339190 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3602. Min Range: -6.3602
Max Act: 6.0477. Min Act: -0.1700
Data Index: 6871538 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3602. Min Range: -6.3602
Max Act: 6.0164. Min Act: -0.1700
Data Index: 5690891 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3602. Min Range: -6.3602
Max Act: 5.9539. Min Act: -0.1700
Data Index: 4880189 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3602. Min Range: -6.3602
Max Act: 5.9539. Min Act: -0.1700
Data Index: 2036937 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3602. Min Range: -6.3602
Max Act: 5.9227. Min Act: -0.1700
Data Index: 7445607 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3602. Min Range: -6.3602
Max Act: 5.9852. Min Act: -0.1700
Data Index: 3275873 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3602. Min Range: -6.3602
Max Act: 5.9227. Min Act: -0.1700
Data Index: 703170 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3602. Min Range: -6.3602
Max Act: 5.9227. Min Act: -0.1700
Data Index: 4805795 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3602. Min Range: -6.3602
Max Act: 5.9227. Min Act: -0.1700
Data Index: 5946592 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3602. Min Range: -6.3602
Max Act: 5.9227. Min Act: -0.1700
Data Index: 4868585 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3602. Min Range: -6.3602
Max Act: 5.9227. Min Act: -0.1700
Data Index: 1011478 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #19