Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2395 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.6972. Min Range: -3.6972
Max Act: 3.6972. Min Act: -0.1700
Data Index: 2954390 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6972. Min Range: -3.6972
Max Act: 3.6659. Min Act: -0.1700
Data Index: 56306 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6972. Min Range: -3.6972
Max Act: 3.6346. Min Act: -0.1700
Data Index: 1533957 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6972. Min Range: -3.6972
Max Act: 3.6346. Min Act: -0.1700
Data Index: 2486810 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6972. Min Range: -3.6972
Max Act: 3.6346. Min Act: -0.1700
Data Index: 7203595 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6972. Min Range: -3.6972
Max Act: 3.5720. Min Act: -0.1700
Data Index: 582602 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6972. Min Range: -3.6972
Max Act: 3.5876. Min Act: -0.1700
Data Index: 631001 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6972. Min Range: -3.6972
Max Act: 3.5563. Min Act: -0.1700
Data Index: 3113833 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6972. Min Range: -3.6972
Max Act: 3.5720. Min Act: -0.1700
Data Index: 8127961 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6972. Min Range: -3.6972
Max Act: 3.5563. Min Act: -0.1700
Data Index: 6376988 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6972. Min Range: -3.6972
Max Act: 3.5563. Min Act: -0.1700
Data Index: 5610906 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6972. Min Range: -3.6972
Max Act: 3.5407. Min Act: -0.1700
Data Index: 8216757 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6972. Min Range: -3.6972
Max Act: 3.5250. Min Act: -0.1700
Data Index: 3567411 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6972. Min Range: -3.6972
Max Act: 3.5094. Min Act: -0.1700
Data Index: 948010 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6972. Min Range: -3.6972
Max Act: 3.4937. Min Act: -0.1700
Data Index: 7323788 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6972. Min Range: -3.6972
Max Act: 3.4937. Min Act: -0.1700
Data Index: 4840886 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6972. Min Range: -3.6972
Max Act: 3.5094. Min Act: -0.1700
Data Index: 4362701 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6972. Min Range: -3.6972
Max Act: 3.4780. Min Act: -0.1700
Data Index: 4301067 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6972. Min Range: -3.6972
Max Act: 3.4624. Min Act: -0.1700
Data Index: 4577767 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6972. Min Range: -3.6972
Max Act: 3.4780. Min Act: -0.1700
Data Index: 7333791 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #19