Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4028 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.1610. Min Range: -4.1610
Max Act: 4.1610. Min Act: -0.1700
Data Index: 940128 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1610. Min Range: -4.1610
Max Act: 4.0047. Min Act: -0.1700
Data Index: 3132364 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1610. Min Range: -4.1610
Max Act: 3.8484. Min Act: -0.1700
Data Index: 1348659 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1610. Min Range: -4.1610
Max Act: 3.8796. Min Act: -0.1700
Data Index: 6353805 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1610. Min Range: -4.1610
Max Act: 3.8327. Min Act: -0.1700
Data Index: 6553999 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1610. Min Range: -4.1610
Max Act: 3.8171. Min Act: -0.1700
Data Index: 1531879 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1610. Min Range: -4.1610
Max Act: 3.8327. Min Act: -0.1700
Data Index: 3880055 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1610. Min Range: -4.1610
Max Act: 3.7702. Min Act: -0.1700
Data Index: 7969967 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1610. Min Range: -4.1610
Max Act: 3.7545. Min Act: -0.1700
Data Index: 3297648 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1610. Min Range: -4.1610
Max Act: 3.7545. Min Act: -0.1700
Data Index: 5391358 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1610. Min Range: -4.1610
Max Act: 3.7545. Min Act: -0.1700
Data Index: 6554000 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1610. Min Range: -4.1610
Max Act: 3.7545. Min Act: -0.1700
Data Index: 3957290 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1610. Min Range: -4.1610
Max Act: 3.7389. Min Act: -0.1700
Data Index: 3882324 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1610. Min Range: -4.1610
Max Act: 3.7702. Min Act: -0.1700
Data Index: 3880053 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1610. Min Range: -4.1610
Max Act: 3.7233. Min Act: -0.1700
Data Index: 4803014 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1610. Min Range: -4.1610
Max Act: 3.7233. Min Act: -0.1700
Data Index: 4592842 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1610. Min Range: -4.1610
Max Act: 3.7233. Min Act: -0.1700
Data Index: 6250693 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1610. Min Range: -4.1610
Max Act: 3.7545. Min Act: -0.1700
Data Index: 6630669 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1610. Min Range: -4.1610
Max Act: 3.7076. Min Act: -0.1700
Data Index: 1460454 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1610. Min Range: -4.1610
Max Act: 3.6920. Min Act: -0.1700
Data Index: 4561174 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #19