Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2870 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8215. Min Range: -6.8215
Max Act: 6.8215. Min Act: -0.1700
Data Index: 1785619 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8215. Min Range: -6.8215
Max Act: 6.6965. Min Act: -0.1700
Data Index: 1257229 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8215. Min Range: -6.8215
Max Act: 6.6340. Min Act: -0.1700
Data Index: 3115876 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8215. Min Range: -6.8215
Max Act: 6.6027. Min Act: -0.1700
Data Index: 2354200 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8215. Min Range: -6.8215
Max Act: 6.6027. Min Act: -0.1700
Data Index: 1369505 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8215. Min Range: -6.8215
Max Act: 6.5402. Min Act: -0.1700
Data Index: 523541 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8215. Min Range: -6.8215
Max Act: 6.4465. Min Act: -0.1700
Data Index: 5501793 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8215. Min Range: -6.8215
Max Act: 6.4465. Min Act: -0.1700
Data Index: 2305222 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8215. Min Range: -6.8215
Max Act: 6.4152. Min Act: -0.1700
Data Index: 1603544 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8215. Min Range: -6.8215
Max Act: 6.3840. Min Act: -0.1700
Data Index: 5913943 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8215. Min Range: -6.8215
Max Act: 6.3527. Min Act: -0.1700
Data Index: 4324303 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8215. Min Range: -6.8215
Max Act: 6.3215. Min Act: -0.1700
Data Index: 1697932 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8215. Min Range: -6.8215
Max Act: 6.3215. Min Act: -0.1700
Data Index: 5250564 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8215. Min Range: -6.8215
Max Act: 6.2902. Min Act: -0.1700
Data Index: 7254936 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8215. Min Range: -6.8215
Max Act: 6.2902. Min Act: -0.1700
Data Index: 2170067 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8215. Min Range: -6.8215
Max Act: 6.2902. Min Act: -0.1700
Data Index: 107066 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8215. Min Range: -6.8215
Max Act: 6.2590. Min Act: -0.1700
Data Index: 3079084 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8215. Min Range: -6.8215
Max Act: 6.2590. Min Act: -0.1700
Data Index: 1078405 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8215. Min Range: -6.8215
Max Act: 6.2902. Min Act: -0.1700
Data Index: 3491352 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8215. Min Range: -6.8215
Max Act: 6.2590. Min Act: -0.1700
Data Index: 484144 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #19