Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.2997. Min Range: -4.2997
Max Act: 4.2997. Min Act: -0.1700
Data Index: 2391351 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2997. Min Range: -4.2997
Max Act: 4.2060. Min Act: -0.1700
Data Index: 835746 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2997. Min Range: -4.2997
Max Act: 4.1747. Min Act: -0.1700
Data Index: 4525791 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2997. Min Range: -4.2997
Max Act: 4.1435. Min Act: -0.1700
Data Index: 1266628 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2997. Min Range: -4.2997
Max Act: 4.1435. Min Act: -0.1700
Data Index: 5869388 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2997. Min Range: -4.2997
Max Act: 4.1122. Min Act: -0.1700
Data Index: 6196299 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2997. Min Range: -4.2997
Max Act: 4.0810. Min Act: -0.1700
Data Index: 7650359 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2997. Min Range: -4.2997
Max Act: 4.1122. Min Act: -0.1700
Data Index: 6803688 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2997. Min Range: -4.2997
Max Act: 4.0810. Min Act: -0.1700
Data Index: 2334697 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2997. Min Range: -4.2997
Max Act: 4.0497. Min Act: -0.1700
Data Index: 2763740 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2997. Min Range: -4.2997
Max Act: 4.0497. Min Act: -0.1700
Data Index: 3039991 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2997. Min Range: -4.2997
Max Act: 4.0810. Min Act: -0.1700
Data Index: 1000275 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2997. Min Range: -4.2997
Max Act: 4.0184. Min Act: -0.1700
Data Index: 2656199 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2997. Min Range: -4.2997
Max Act: 4.0184. Min Act: -0.1700
Data Index: 8228200 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2997. Min Range: -4.2997
Max Act: 4.0184. Min Act: -0.1700
Data Index: 6890134 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2997. Min Range: -4.2997
Max Act: 3.9872. Min Act: -0.1700
Data Index: 6506002 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2997. Min Range: -4.2997
Max Act: 3.9872. Min Act: -0.1700
Data Index: 3287899 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2997. Min Range: -4.2997
Max Act: 3.9872. Min Act: -0.1700
Data Index: 3495932 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2997. Min Range: -4.2997
Max Act: 3.9559. Min Act: -0.1700
Data Index: 6840135 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2997. Min Range: -4.2997
Max Act: 3.9872. Min Act: -0.1700
Data Index: 6350781 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #19