Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3496 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2056. Min Range: -6.2056
Max Act: 6.2056. Min Act: -0.1700
Data Index: 4952640 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2056. Min Range: -6.2056
Max Act: 6.1431. Min Act: -0.1700
Data Index: 3493520 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2056. Min Range: -6.2056
Max Act: 6.1118. Min Act: -0.1700
Data Index: 1772492 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2056. Min Range: -6.2056
Max Act: 6.0493. Min Act: -0.1700
Data Index: 2786264 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2056. Min Range: -6.2056
Max Act: 5.9556. Min Act: -0.1700
Data Index: 1955571 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2056. Min Range: -6.2056
Max Act: 5.9243. Min Act: -0.1700
Data Index: 1879947 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2056. Min Range: -6.2056
Max Act: 5.8931. Min Act: -0.1700
Data Index: 5876347 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2056. Min Range: -6.2056
Max Act: 5.9556. Min Act: -0.1700
Data Index: 2459742 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2056. Min Range: -6.2056
Max Act: 5.8306. Min Act: -0.1700
Data Index: 5307891 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2056. Min Range: -6.2056
Max Act: 5.7681. Min Act: -0.1700
Data Index: 7068347 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2056. Min Range: -6.2056
Max Act: 5.7681. Min Act: -0.1700
Data Index: 2086874 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2056. Min Range: -6.2056
Max Act: 5.7368. Min Act: -0.1700
Data Index: 2425011 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2056. Min Range: -6.2056
Max Act: 5.7368. Min Act: -0.1700
Data Index: 800963 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2056. Min Range: -6.2056
Max Act: 5.7056. Min Act: -0.1700
Data Index: 2003298 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2056. Min Range: -6.2056
Max Act: 5.6743. Min Act: -0.1700
Data Index: 7218601 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2056. Min Range: -6.2056
Max Act: 5.6431. Min Act: -0.1700
Data Index: 459566 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2056. Min Range: -6.2056
Max Act: 5.6118. Min Act: -0.1700
Data Index: 959402 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2056. Min Range: -6.2056
Max Act: 5.6118. Min Act: -0.1700
Data Index: 2497203 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2056. Min Range: -6.2056
Max Act: 5.6431. Min Act: -0.1700
Data Index: 4535794 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2056. Min Range: -6.2056
Max Act: 5.5806. Min Act: -0.1700
Data Index: 2185472 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #19