Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2023 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7592. Min Range: -5.7592
Max Act: 5.7592. Min Act: -0.1700
Data Index: 7086375 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7592. Min Range: -5.7592
Max Act: 5.7592. Min Act: -0.1700
Data Index: 7086376 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7592. Min Range: -5.7592
Max Act: 5.6967. Min Act: -0.1700
Data Index: 7007980 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7592. Min Range: -5.7592
Max Act: 5.6342. Min Act: -0.1700
Data Index: 7845487 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7592. Min Range: -5.7592
Max Act: 5.5717. Min Act: -0.1700
Data Index: 7086374 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7592. Min Range: -5.7592
Max Act: 5.5404. Min Act: -0.1700
Data Index: 5997379 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7592. Min Range: -5.7592
Max Act: 5.5404. Min Act: -0.1700
Data Index: 3143341 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7592. Min Range: -5.7592
Max Act: 5.5404. Min Act: -0.1700
Data Index: 3228162 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7592. Min Range: -5.7592
Max Act: 5.5092. Min Act: -0.1700
Data Index: 3674684 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7592. Min Range: -5.7592
Max Act: 5.4779. Min Act: -0.1700
Data Index: 8376826 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7592. Min Range: -5.7592
Max Act: 5.4467. Min Act: -0.1700
Data Index: 5852820 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7592. Min Range: -5.7592
Max Act: 5.4779. Min Act: -0.1700
Data Index: 3006618 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7592. Min Range: -5.7592
Max Act: 5.4154. Min Act: -0.1700
Data Index: 6808213 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7592. Min Range: -5.7592
Max Act: 5.3842. Min Act: -0.1700
Data Index: 2995997 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7592. Min Range: -5.7592
Max Act: 5.3842. Min Act: -0.1700
Data Index: 5582779 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7592. Min Range: -5.7592
Max Act: 5.3529. Min Act: -0.1700
Data Index: 4597593 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7592. Min Range: -5.7592
Max Act: 5.3529. Min Act: -0.1700
Data Index: 35215 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7592. Min Range: -5.7592
Max Act: 5.3529. Min Act: -0.1700
Data Index: 8330543 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7592. Min Range: -5.7592
Max Act: 5.3529. Min Act: -0.1700
Data Index: 477604 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7592. Min Range: -5.7592
Max Act: 5.3529. Min Act: -0.1700
Data Index: 707002 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #19