Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 27 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2592. Min Range: -6.2592
Max Act: 6.2592. Min Act: -0.1700
Data Index: 6252293 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2592. Min Range: -6.2592
Max Act: 6.2280. Min Act: -0.1700
Data Index: 8345256 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2592. Min Range: -6.2592
Max Act: 6.1655. Min Act: -0.1700
Data Index: 650748 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2592. Min Range: -6.2592
Max Act: 6.1030. Min Act: -0.1700
Data Index: 3225085 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2592. Min Range: -6.2592
Max Act: 6.0405. Min Act: -0.1700
Data Index: 2541633 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2592. Min Range: -6.2592
Max Act: 6.0717. Min Act: -0.1700
Data Index: 5531288 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2592. Min Range: -6.2592
Max Act: 5.9467. Min Act: -0.1700
Data Index: 4130737 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2592. Min Range: -6.2592
Max Act: 5.8842. Min Act: -0.1700
Data Index: 7763568 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2592. Min Range: -6.2592
Max Act: 5.8530. Min Act: -0.1700
Data Index: 1120650 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2592. Min Range: -6.2592
Max Act: 5.8530. Min Act: -0.1700
Data Index: 3678831 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2592. Min Range: -6.2592
Max Act: 5.8530. Min Act: -0.1700
Data Index: 7311374 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2592. Min Range: -6.2592
Max Act: 5.8530. Min Act: -0.1700
Data Index: 4556291 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2592. Min Range: -6.2592
Max Act: 5.8217. Min Act: -0.1700
Data Index: 6853152 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2592. Min Range: -6.2592
Max Act: 5.8530. Min Act: -0.1700
Data Index: 2677848 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2592. Min Range: -6.2592
Max Act: 5.7905. Min Act: -0.1700
Data Index: 1005646 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2592. Min Range: -6.2592
Max Act: 5.7280. Min Act: -0.1700
Data Index: 2620685 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2592. Min Range: -6.2592
Max Act: 5.7905. Min Act: -0.1700
Data Index: 1538538 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2592. Min Range: -6.2592
Max Act: 5.7280. Min Act: -0.1700
Data Index: 3398814 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2592. Min Range: -6.2592
Max Act: 5.7592. Min Act: -0.1700
Data Index: 6704919 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2592. Min Range: -6.2592
Max Act: 5.7280. Min Act: -0.1700
Data Index: 4399714 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #19