Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3280 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5365. Min Range: -6.5365
Max Act: 6.5365. Min Act: -0.1700
Data Index: 970707 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5365. Min Range: -6.5365
Max Act: 6.5053. Min Act: -0.1700
Data Index: 2491121 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5365. Min Range: -6.5365
Max Act: 6.5365. Min Act: -0.1700
Data Index: 2732228 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5365. Min Range: -6.5365
Max Act: 6.2553. Min Act: -0.1700
Data Index: 486605 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5365. Min Range: -6.5365
Max Act: 6.1615. Min Act: -0.1700
Data Index: 7112823 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5365. Min Range: -6.5365
Max Act: 6.1303. Min Act: -0.1700
Data Index: 7008610 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5365. Min Range: -6.5365
Max Act: 6.1303. Min Act: -0.1700
Data Index: 6784031 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5365. Min Range: -6.5365
Max Act: 6.0678. Min Act: -0.1700
Data Index: 4263739 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5365. Min Range: -6.5365
Max Act: 6.0990. Min Act: -0.1700
Data Index: 1519076 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5365. Min Range: -6.5365
Max Act: 6.0990. Min Act: -0.1700
Data Index: 7376515 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5365. Min Range: -6.5365
Max Act: 6.0678. Min Act: -0.1700
Data Index: 3520355 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5365. Min Range: -6.5365
Max Act: 6.0365. Min Act: -0.1700
Data Index: 8378907 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5365. Min Range: -6.5365
Max Act: 6.0678. Min Act: -0.1700
Data Index: 625017 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5365. Min Range: -6.5365
Max Act: 6.0678. Min Act: -0.1700
Data Index: 4623616 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5365. Min Range: -6.5365
Max Act: 6.0678. Min Act: -0.1700
Data Index: 8391141 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5365. Min Range: -6.5365
Max Act: 6.0678. Min Act: -0.1700
Data Index: 7089389 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5365. Min Range: -6.5365
Max Act: 6.0678. Min Act: -0.1700
Data Index: 1892156 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5365. Min Range: -6.5365
Max Act: 6.0365. Min Act: -0.1700
Data Index: 747211 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5365. Min Range: -6.5365
Max Act: 6.0365. Min Act: -0.1700
Data Index: 6441957 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5365. Min Range: -6.5365
Max Act: 6.0053. Min Act: -0.1700
Data Index: 6672234 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #19