Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4017 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0920. Min Range: -7.0920
Max Act: 7.0920. Min Act: -0.1700
Data Index: 8029384 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0920. Min Range: -7.0920
Max Act: 7.0608. Min Act: -0.1700
Data Index: 243269 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0920. Min Range: -7.0920
Max Act: 6.9670. Min Act: -0.1700
Data Index: 4851293 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0920. Min Range: -7.0920
Max Act: 6.9045. Min Act: -0.1700
Data Index: 8439307 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0920. Min Range: -7.0920
Max Act: 6.7795. Min Act: -0.1700
Data Index: 5444399 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0920. Min Range: -7.0920
Max Act: 6.7795. Min Act: -0.1700
Data Index: 3561899 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0920. Min Range: -7.0920
Max Act: 6.7483. Min Act: -0.1700
Data Index: 4623594 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0920. Min Range: -7.0920
Max Act: 6.7483. Min Act: -0.1700
Data Index: 3035519 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0920. Min Range: -7.0920
Max Act: 6.6858. Min Act: -0.1700
Data Index: 2697600 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0920. Min Range: -7.0920
Max Act: 6.7170. Min Act: -0.1700
Data Index: 4551440 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0920. Min Range: -7.0920
Max Act: 6.6858. Min Act: -0.1700
Data Index: 5750670 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0920. Min Range: -7.0920
Max Act: 6.6545. Min Act: -0.1700
Data Index: 2059795 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0920. Min Range: -7.0920
Max Act: 6.6545. Min Act: -0.1700
Data Index: 5502726 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0920. Min Range: -7.0920
Max Act: 6.6545. Min Act: -0.1700
Data Index: 8250283 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0920. Min Range: -7.0920
Max Act: 6.6545. Min Act: -0.1700
Data Index: 6862450 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0920. Min Range: -7.0920
Max Act: 6.6545. Min Act: -0.1700
Data Index: 6758310 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0920. Min Range: -7.0920
Max Act: 6.5920. Min Act: -0.1700
Data Index: 7991170 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0920. Min Range: -7.0920
Max Act: 6.6233. Min Act: -0.1700
Data Index: 4135278 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0920. Min Range: -7.0920
Max Act: 6.6233. Min Act: -0.1700
Data Index: 3472621 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0920. Min Range: -7.0920
Max Act: 6.6233. Min Act: -0.1700
Data Index: 1814289 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #19