Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4098 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6643. Min Range: -5.6643
Max Act: 5.6643. Min Act: -0.1700
Data Index: 8421971 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6643. Min Range: -5.6643
Max Act: 5.6330. Min Act: -0.1700
Data Index: 1557451 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6643. Min Range: -5.6643
Max Act: 5.5705. Min Act: -0.1700
Data Index: 7068104 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6643. Min Range: -5.6643
Max Act: 5.5705. Min Act: -0.1700
Data Index: 724806 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6643. Min Range: -5.6643
Max Act: 5.5705. Min Act: -0.1700
Data Index: 4695542 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6643. Min Range: -5.6643
Max Act: 5.5705. Min Act: -0.1700
Data Index: 8021263 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6643. Min Range: -5.6643
Max Act: 5.5080. Min Act: -0.1700
Data Index: 2135560 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6643. Min Range: -5.6643
Max Act: 5.5080. Min Act: -0.1700
Data Index: 4695541 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6643. Min Range: -5.6643
Max Act: 5.4768. Min Act: -0.1700
Data Index: 8485998 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6643. Min Range: -5.6643
Max Act: 5.4768. Min Act: -0.1700
Data Index: 6106839 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6643. Min Range: -5.6643
Max Act: 5.4768. Min Act: -0.1700
Data Index: 4671984 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6643. Min Range: -5.6643
Max Act: 5.4455. Min Act: -0.1700
Data Index: 1167894 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6643. Min Range: -5.6643
Max Act: 5.4143. Min Act: -0.1700
Data Index: 3693791 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6643. Min Range: -5.6643
Max Act: 5.4455. Min Act: -0.1700
Data Index: 7274658 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6643. Min Range: -5.6643
Max Act: 5.4455. Min Act: -0.1700
Data Index: 4467888 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6643. Min Range: -5.6643
Max Act: 5.4143. Min Act: -0.1700
Data Index: 632803 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6643. Min Range: -5.6643
Max Act: 5.3830. Min Act: -0.1700
Data Index: 8777687 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6643. Min Range: -5.6643
Max Act: 5.4143. Min Act: -0.1700
Data Index: 1856118 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6643. Min Range: -5.6643
Max Act: 5.3830. Min Act: -0.1700
Data Index: 935069 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6643. Min Range: -5.6643
Max Act: 5.3830. Min Act: -0.1700
Data Index: 897973 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #19