Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1747 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.5552. Min Range: -3.5552
Max Act: 3.5552. Min Act: -0.1700
Data Index: 7331550 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5552. Min Range: -3.5552
Max Act: 3.5239. Min Act: -0.1700
Data Index: 8701921 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5552. Min Range: -3.5552
Max Act: 3.3672. Min Act: -0.1700
Data Index: 7255164 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5552. Min Range: -3.5552
Max Act: 3.3201. Min Act: -0.1700
Data Index: 106848 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5552. Min Range: -3.5552
Max Act: 3.3201. Min Act: -0.1700
Data Index: 6253109 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5552. Min Range: -3.5552
Max Act: 3.3044. Min Act: -0.1700
Data Index: 5994953 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5552. Min Range: -3.5552
Max Act: 3.3201. Min Act: -0.1700
Data Index: 4564253 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5552. Min Range: -3.5552
Max Act: 3.3044. Min Act: -0.1700
Data Index: 7648377 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5552. Min Range: -3.5552
Max Act: 3.2730. Min Act: -0.1700
Data Index: 1081154 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5552. Min Range: -3.5552
Max Act: 3.2730. Min Act: -0.1700
Data Index: 4970766 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5552. Min Range: -3.5552
Max Act: 3.2730. Min Act: -0.1700
Data Index: 840657 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5552. Min Range: -3.5552
Max Act: 3.2730. Min Act: -0.1700
Data Index: 7388853 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5552. Min Range: -3.5552
Max Act: 3.2573. Min Act: -0.1700
Data Index: 8656190 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5552. Min Range: -3.5552
Max Act: 3.2573. Min Act: -0.1700
Data Index: 7469427 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5552. Min Range: -3.5552
Max Act: 3.2573. Min Act: -0.1700
Data Index: 2313607 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5552. Min Range: -3.5552
Max Act: 3.2416. Min Act: -0.1700
Data Index: 1753873 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5552. Min Range: -3.5552
Max Act: 3.2259. Min Act: -0.1700
Data Index: 7586126 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5552. Min Range: -3.5552
Max Act: 3.2416. Min Act: -0.1700
Data Index: 297303 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5552. Min Range: -3.5552
Max Act: 3.2259. Min Act: -0.1700
Data Index: 4971540 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5552. Min Range: -3.5552
Max Act: 3.2259. Min Act: -0.1700
Data Index: 31852 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #19