Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2985 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1679. Min Range: -5.1679
Max Act: 5.1366. Min Act: -0.1700
Data Index: 883144 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1679. Min Range: -5.1679
Max Act: 5.1679. Min Act: -0.1700
Data Index: 6321911 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1679. Min Range: -5.1679
Max Act: 5.1366. Min Act: -0.1700
Data Index: 168634 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1679. Min Range: -5.1679
Max Act: 5.1366. Min Act: -0.1700
Data Index: 7094315 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1679. Min Range: -5.1679
Max Act: 5.0741. Min Act: -0.1700
Data Index: 2669663 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1679. Min Range: -5.1679
Max Act: 5.0429. Min Act: -0.1700
Data Index: 4118814 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1679. Min Range: -5.1679
Max Act: 5.0429. Min Act: -0.1700
Data Index: 5223225 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1679. Min Range: -5.1679
Max Act: 5.0429. Min Act: -0.1700
Data Index: 7570455 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1679. Min Range: -5.1679
Max Act: 5.0116. Min Act: -0.1700
Data Index: 8183903 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1679. Min Range: -5.1679
Max Act: 4.9804. Min Act: -0.1700
Data Index: 6716133 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1679. Min Range: -5.1679
Max Act: 4.9804. Min Act: -0.1700
Data Index: 2487040 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1679. Min Range: -5.1679
Max Act: 4.9804. Min Act: -0.1700
Data Index: 8823163 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1679. Min Range: -5.1679
Max Act: 4.9491. Min Act: -0.1700
Data Index: 8771104 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1679. Min Range: -5.1679
Max Act: 4.9179. Min Act: -0.1700
Data Index: 1106104 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1679. Min Range: -5.1679
Max Act: 4.9179. Min Act: -0.1700
Data Index: 8080449 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1679. Min Range: -5.1679
Max Act: 4.9179. Min Act: -0.1700
Data Index: 4074496 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1679. Min Range: -5.1679
Max Act: 4.8866. Min Act: -0.1700
Data Index: 6038823 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1679. Min Range: -5.1679
Max Act: 4.8866. Min Act: -0.1700
Data Index: 957493 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1679. Min Range: -5.1679
Max Act: 4.8866. Min Act: -0.1700
Data Index: 1196565 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1679. Min Range: -5.1679
Max Act: 4.8866. Min Act: -0.1700
Data Index: 964721 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #19