Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2133 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.7663. Min Range: -3.7663
Max Act: 3.7663. Min Act: -0.1700
Data Index: 6169920 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7663. Min Range: -3.7663
Max Act: 3.6568. Min Act: -0.1700
Data Index: 7451818 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7663. Min Range: -3.7663
Max Act: 3.5942. Min Act: -0.1700
Data Index: 1690855 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7663. Min Range: -3.7663
Max Act: 3.5786. Min Act: -0.1700
Data Index: 1794969 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7663. Min Range: -3.7663
Max Act: 3.5316. Min Act: -0.1700
Data Index: 5633952 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7663. Min Range: -3.7663
Max Act: 3.5003. Min Act: -0.1700
Data Index: 725055 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7663. Min Range: -3.7663
Max Act: 3.4846. Min Act: -0.1700
Data Index: 8380802 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7663. Min Range: -3.7663
Max Act: 3.4846. Min Act: -0.1700
Data Index: 7114276 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7663. Min Range: -3.7663
Max Act: 3.5003. Min Act: -0.1700
Data Index: 6581162 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7663. Min Range: -3.7663
Max Act: 3.4376. Min Act: -0.1700
Data Index: 4723508 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7663. Min Range: -3.7663
Max Act: 3.4690. Min Act: -0.1700
Data Index: 3516434 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7663. Min Range: -3.7663
Max Act: 3.4533. Min Act: -0.1700
Data Index: 8725074 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7663. Min Range: -3.7663
Max Act: 3.4533. Min Act: -0.1700
Data Index: 6059947 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7663. Min Range: -3.7663
Max Act: 3.4533. Min Act: -0.1700
Data Index: 8725062 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7663. Min Range: -3.7663
Max Act: 3.4376. Min Act: -0.1700
Data Index: 7052932 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7663. Min Range: -3.7663
Max Act: 3.4220. Min Act: -0.1700
Data Index: 3126654 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7663. Min Range: -3.7663
Max Act: 3.4063. Min Act: -0.1700
Data Index: 6523918 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7663. Min Range: -3.7663
Max Act: 3.3906. Min Act: -0.1700
Data Index: 3188732 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7663. Min Range: -3.7663
Max Act: 3.4063. Min Act: -0.1700
Data Index: 3795024 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7663. Min Range: -3.7663
Max Act: 3.3749. Min Act: -0.1700
Data Index: 3787650 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #19