Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 757 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.2674. Min Range: -3.2674
Max Act: 3.2674. Min Act: -0.1700
Data Index: 352059 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2674. Min Range: -3.2674
Max Act: 3.2359. Min Act: -0.1700
Data Index: 5406790 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2674. Min Range: -3.2674
Max Act: 3.1730. Min Act: -0.1700
Data Index: 4409812 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2674. Min Range: -3.2674
Max Act: 3.1573. Min Act: -0.1700
Data Index: 5793489 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2674. Min Range: -3.2674
Max Act: 3.1888. Min Act: -0.1700
Data Index: 2832433 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2674. Min Range: -3.2674
Max Act: 3.1730. Min Act: -0.1700
Data Index: 2718903 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2674. Min Range: -3.2674
Max Act: 3.1573. Min Act: -0.1700
Data Index: 7342581 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2674. Min Range: -3.2674
Max Act: 3.1416. Min Act: -0.1700
Data Index: 7826490 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2674. Min Range: -3.2674
Max Act: 3.1258. Min Act: -0.1700
Data Index: 1464338 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2674. Min Range: -3.2674
Max Act: 3.1258. Min Act: -0.1700
Data Index: 641705 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2674. Min Range: -3.2674
Max Act: 3.1100. Min Act: -0.1700
Data Index: 2865346 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2674. Min Range: -3.2674
Max Act: 3.1258. Min Act: -0.1700
Data Index: 4845038 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2674. Min Range: -3.2674
Max Act: 3.1258. Min Act: -0.1700
Data Index: 5121887 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2674. Min Range: -3.2674
Max Act: 3.0943. Min Act: -0.1700
Data Index: 4538655 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2674. Min Range: -3.2674
Max Act: 3.1100. Min Act: -0.1700
Data Index: 1069394 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2674. Min Range: -3.2674
Max Act: 3.1100. Min Act: -0.1700
Data Index: 1019269 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2674. Min Range: -3.2674
Max Act: 3.1100. Min Act: -0.1700
Data Index: 8587196 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2674. Min Range: -3.2674
Max Act: 3.0943. Min Act: -0.1700
Data Index: 7787112 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2674. Min Range: -3.2674
Max Act: 3.0628. Min Act: -0.1700
Data Index: 7709145 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2674. Min Range: -3.2674
Max Act: 3.0628. Min Act: -0.1700
Data Index: 1464299 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #19