Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1996 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2706. Min Range: -6.2706
Max Act: 6.2706. Min Act: -0.1700
Data Index: 3542385 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2706. Min Range: -6.2706
Max Act: 6.2081. Min Act: -0.1700
Data Index: 6075662 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2706. Min Range: -6.2706
Max Act: 6.1456. Min Act: -0.1700
Data Index: 143139 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2706. Min Range: -6.2706
Max Act: 6.1143. Min Act: -0.1700
Data Index: 8462224 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2706. Min Range: -6.2706
Max Act: 6.1456. Min Act: -0.1700
Data Index: 7538426 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2706. Min Range: -6.2706
Max Act: 6.1143. Min Act: -0.1700
Data Index: 3524167 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2706. Min Range: -6.2706
Max Act: 6.0831. Min Act: -0.1700
Data Index: 5381218 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2706. Min Range: -6.2706
Max Act: 6.0518. Min Act: -0.1700
Data Index: 5696291 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2706. Min Range: -6.2706
Max Act: 6.0206. Min Act: -0.1700
Data Index: 309902 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2706. Min Range: -6.2706
Max Act: 5.9893. Min Act: -0.1700
Data Index: 6609345 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2706. Min Range: -6.2706
Max Act: 5.9581. Min Act: -0.1700
Data Index: 2934513 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2706. Min Range: -6.2706
Max Act: 5.9581. Min Act: -0.1700
Data Index: 2685366 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2706. Min Range: -6.2706
Max Act: 5.9581. Min Act: -0.1700
Data Index: 925984 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2706. Min Range: -6.2706
Max Act: 5.9268. Min Act: -0.1700
Data Index: 319995 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2706. Min Range: -6.2706
Max Act: 5.9581. Min Act: -0.1700
Data Index: 8272543 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2706. Min Range: -6.2706
Max Act: 5.8331. Min Act: -0.1700
Data Index: 7824933 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2706. Min Range: -6.2706
Max Act: 5.8956. Min Act: -0.1700
Data Index: 7359012 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2706. Min Range: -6.2706
Max Act: 5.8643. Min Act: -0.1700
Data Index: 6683333 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2706. Min Range: -6.2706
Max Act: 5.8643. Min Act: -0.1700
Data Index: 4348579 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2706. Min Range: -6.2706
Max Act: 5.8643. Min Act: -0.1700
Data Index: 3657018 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #19