Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4388 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6609. Min Range: -5.6609
Max Act: 5.6609. Min Act: -0.1700
Data Index: 6926997 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6609. Min Range: -5.6609
Max Act: 5.5984. Min Act: -0.1700
Data Index: 3137259 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6609. Min Range: -5.6609
Max Act: 5.5984. Min Act: -0.1700
Data Index: 5675813 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6609. Min Range: -5.6609
Max Act: 5.5672. Min Act: -0.1700
Data Index: 2415128 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6609. Min Range: -5.6609
Max Act: 5.5047. Min Act: -0.1700
Data Index: 4509784 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6609. Min Range: -5.6609
Max Act: 5.4109. Min Act: -0.1700
Data Index: 2108391 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6609. Min Range: -5.6609
Max Act: 5.4109. Min Act: -0.1700
Data Index: 777032 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6609. Min Range: -5.6609
Max Act: 5.3797. Min Act: -0.1700
Data Index: 104594 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6609. Min Range: -5.6609
Max Act: 5.3797. Min Act: -0.1700
Data Index: 576874 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6609. Min Range: -5.6609
Max Act: 5.2859. Min Act: -0.1700
Data Index: 106634 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6609. Min Range: -5.6609
Max Act: 5.2234. Min Act: -0.1700
Data Index: 1239405 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6609. Min Range: -5.6609
Max Act: 5.2234. Min Act: -0.1700
Data Index: 2496797 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6609. Min Range: -5.6609
Max Act: 5.2547. Min Act: -0.1700
Data Index: 2174681 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6609. Min Range: -5.6609
Max Act: 5.2234. Min Act: -0.1700
Data Index: 941830 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6609. Min Range: -5.6609
Max Act: 5.2234. Min Act: -0.1700
Data Index: 8009121 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6609. Min Range: -5.6609
Max Act: 5.1609. Min Act: -0.1700
Data Index: 2784448 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6609. Min Range: -5.6609
Max Act: 5.1609. Min Act: -0.1700
Data Index: 671658 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6609. Min Range: -5.6609
Max Act: 5.1297. Min Act: -0.1700
Data Index: 6056357 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6609. Min Range: -5.6609
Max Act: 5.1297. Min Act: -0.1700
Data Index: 8204348 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6609. Min Range: -5.6609
Max Act: 5.0984. Min Act: -0.1700
Data Index: 7126352 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #19