Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1558 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3619. Min Range: -7.3619
Max Act: 7.3619. Min Act: -0.1700
Data Index: 7473637 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3619. Min Range: -7.3619
Max Act: 6.8619. Min Act: -0.1700
Data Index: 1271188 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3619. Min Range: -7.3619
Max Act: 6.8306. Min Act: -0.1700
Data Index: 125892 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3619. Min Range: -7.3619
Max Act: 6.7994. Min Act: -0.1700
Data Index: 2046005 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3619. Min Range: -7.3619
Max Act: 6.7681. Min Act: -0.1700
Data Index: 5981807 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3619. Min Range: -7.3619
Max Act: 6.7681. Min Act: -0.1700
Data Index: 496369 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3619. Min Range: -7.3619
Max Act: 6.7056. Min Act: -0.1700
Data Index: 7508987 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3619. Min Range: -7.3619
Max Act: 6.6744. Min Act: -0.1700
Data Index: 5877639 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3619. Min Range: -7.3619
Max Act: 6.6119. Min Act: -0.1700
Data Index: 8465183 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3619. Min Range: -7.3619
Max Act: 6.6431. Min Act: -0.1700
Data Index: 1252846 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3619. Min Range: -7.3619
Max Act: 6.5181. Min Act: -0.1700
Data Index: 420401 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3619. Min Range: -7.3619
Max Act: 6.5181. Min Act: -0.1700
Data Index: 8156767 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3619. Min Range: -7.3619
Max Act: 6.4869. Min Act: -0.1700
Data Index: 2420013 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3619. Min Range: -7.3619
Max Act: 6.4869. Min Act: -0.1700
Data Index: 2317593 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3619. Min Range: -7.3619
Max Act: 6.4869. Min Act: -0.1700
Data Index: 704550 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3619. Min Range: -7.3619
Max Act: 6.4556. Min Act: -0.1700
Data Index: 467565 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3619. Min Range: -7.3619
Max Act: 6.4869. Min Act: -0.1700
Data Index: 6420671 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3619. Min Range: -7.3619
Max Act: 6.4556. Min Act: -0.1700
Data Index: 787481 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3619. Min Range: -7.3619
Max Act: 6.3931. Min Act: -0.1700
Data Index: 4176777 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3619. Min Range: -7.3619
Max Act: 6.3931. Min Act: -0.1700
Data Index: 547009 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #19