Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4374 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.5453. Min Range: -8.5453
Max Act: 8.5453. Min Act: -0.1700
Data Index: 5677654 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5453. Min Range: -8.5453
Max Act: 8.2953. Min Act: -0.1700
Data Index: 438595 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5453. Min Range: -8.5453
Max Act: 8.1078. Min Act: -0.1700
Data Index: 1520546 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5453. Min Range: -8.5453
Max Act: 8.1078. Min Act: -0.1700
Data Index: 7058278 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5453. Min Range: -8.5453
Max Act: 8.0453. Min Act: -0.1700
Data Index: 4025245 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5453. Min Range: -8.5453
Max Act: 7.9828. Min Act: -0.1700
Data Index: 2117911 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5453. Min Range: -8.5453
Max Act: 8.0453. Min Act: -0.1700
Data Index: 2278687 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5453. Min Range: -8.5453
Max Act: 7.9203. Min Act: -0.1700
Data Index: 4591248 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5453. Min Range: -8.5453
Max Act: 7.9203. Min Act: -0.1700
Data Index: 1312383 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5453. Min Range: -8.5453
Max Act: 7.8578. Min Act: -0.1700
Data Index: 4882374 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5453. Min Range: -8.5453
Max Act: 7.8890. Min Act: -0.1700
Data Index: 6023739 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5453. Min Range: -8.5453
Max Act: 7.7953. Min Act: -0.1700
Data Index: 5246185 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5453. Min Range: -8.5453
Max Act: 7.7640. Min Act: -0.1700
Data Index: 8044892 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5453. Min Range: -8.5453
Max Act: 7.7640. Min Act: -0.1700
Data Index: 4052032 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5453. Min Range: -8.5453
Max Act: 7.7640. Min Act: -0.1700
Data Index: 3391521 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5453. Min Range: -8.5453
Max Act: 7.7328. Min Act: -0.1700
Data Index: 2493369 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5453. Min Range: -8.5453
Max Act: 7.7328. Min Act: -0.1700
Data Index: 2761854 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5453. Min Range: -8.5453
Max Act: 7.7328. Min Act: -0.1700
Data Index: 3079424 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5453. Min Range: -8.5453
Max Act: 7.7328. Min Act: -0.1700
Data Index: 6942855 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5453. Min Range: -8.5453
Max Act: 7.7328. Min Act: -0.1700
Data Index: 6539971 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #19