Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6390 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4575. Min Range: -7.4575
Max Act: 7.4575. Min Act: -0.1700
Data Index: 2834997 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4575. Min Range: -7.4575
Max Act: 7.4263. Min Act: -0.1700
Data Index: 6174709 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4575. Min Range: -7.4575
Max Act: 7.2388. Min Act: -0.1700
Data Index: 5331600 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4575. Min Range: -7.4575
Max Act: 7.2075. Min Act: -0.1700
Data Index: 8769585 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4575. Min Range: -7.4575
Max Act: 7.1763. Min Act: -0.1700
Data Index: 8003743 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4575. Min Range: -7.4575
Max Act: 7.1138. Min Act: -0.1700
Data Index: 8022622 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4575. Min Range: -7.4575
Max Act: 7.1138. Min Act: -0.1700
Data Index: 6075928 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4575. Min Range: -7.4575
Max Act: 7.1138. Min Act: -0.1700
Data Index: 2739903 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4575. Min Range: -7.4575
Max Act: 7.1138. Min Act: -0.1700
Data Index: 2001647 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4575. Min Range: -7.4575
Max Act: 7.0200. Min Act: -0.1700
Data Index: 8528560 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4575. Min Range: -7.4575
Max Act: 7.0513. Min Act: -0.1700
Data Index: 7010934 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4575. Min Range: -7.4575
Max Act: 7.0200. Min Act: -0.1700
Data Index: 7532882 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4575. Min Range: -7.4575
Max Act: 6.9888. Min Act: -0.1700
Data Index: 4547109 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4575. Min Range: -7.4575
Max Act: 6.9575. Min Act: -0.1700
Data Index: 5918347 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4575. Min Range: -7.4575
Max Act: 6.9575. Min Act: -0.1700
Data Index: 5744106 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4575. Min Range: -7.4575
Max Act: 6.9575. Min Act: -0.1700
Data Index: 450316 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4575. Min Range: -7.4575
Max Act: 6.9263. Min Act: -0.1700
Data Index: 6715570 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4575. Min Range: -7.4575
Max Act: 6.9575. Min Act: -0.1700
Data Index: 4603629 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4575. Min Range: -7.4575
Max Act: 6.8638. Min Act: -0.1700
Data Index: 1818340 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4575. Min Range: -7.4575
Max Act: 6.8013. Min Act: -0.1700
Data Index: 1783350 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #19