Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3497 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9821. Min Range: -7.9821
Max Act: 7.9821. Min Act: -0.1700
Data Index: 1729428 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9821. Min Range: -7.9821
Max Act: 7.9821. Min Act: -0.1700
Data Index: 959523 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9821. Min Range: -7.9821
Max Act: 7.9196. Min Act: -0.1700
Data Index: 1562479 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9821. Min Range: -7.9821
Max Act: 7.9196. Min Act: -0.1700
Data Index: 4577743 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9821. Min Range: -7.9821
Max Act: 7.9196. Min Act: -0.1700
Data Index: 5140932 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9821. Min Range: -7.9821
Max Act: 7.9196. Min Act: -0.1700
Data Index: 2271720 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9821. Min Range: -7.9821
Max Act: 7.7946. Min Act: -0.1700
Data Index: 895732 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9821. Min Range: -7.9821
Max Act: 7.7946. Min Act: -0.1700
Data Index: 1779527 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9821. Min Range: -7.9821
Max Act: 7.8571. Min Act: -0.1700
Data Index: 4111021 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9821. Min Range: -7.9821
Max Act: 7.7321. Min Act: -0.1700
Data Index: 4077 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9821. Min Range: -7.9821
Max Act: 7.7321. Min Act: -0.1700
Data Index: 3092027 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9821. Min Range: -7.9821
Max Act: 7.7321. Min Act: -0.1700
Data Index: 392793 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9821. Min Range: -7.9821
Max Act: 7.7321. Min Act: -0.1700
Data Index: 6722505 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9821. Min Range: -7.9821
Max Act: 7.7946. Min Act: -0.1700
Data Index: 6584710 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9821. Min Range: -7.9821
Max Act: 7.6696. Min Act: -0.1700
Data Index: 796202 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9821. Min Range: -7.9821
Max Act: 7.6696. Min Act: -0.1700
Data Index: 4127877 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9821. Min Range: -7.9821
Max Act: 7.6696. Min Act: -0.1700
Data Index: 1341862 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9821. Min Range: -7.9821
Max Act: 7.6696. Min Act: -0.1700
Data Index: 2044325 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9821. Min Range: -7.9821
Max Act: 7.6696. Min Act: -0.1700
Data Index: 3314953 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9821. Min Range: -7.9821
Max Act: 7.6696. Min Act: -0.1700
Data Index: 4712611 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #19