Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1657 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.7041. Min Range: -2.7041
Max Act: 2.7041. Min Act: -0.1700
Data Index: 3795618 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7041. Min Range: -2.7041
Max Act: 2.7041. Min Act: -0.1700
Data Index: 4135274 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7041. Min Range: -2.7041
Max Act: 2.6881. Min Act: -0.1700
Data Index: 8708315 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7041. Min Range: -2.7041
Max Act: 2.6881. Min Act: -0.1700
Data Index: 4287362 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7041. Min Range: -2.7041
Max Act: 2.6720. Min Act: -0.1700
Data Index: 7328415 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7041. Min Range: -2.7041
Max Act: 2.6400. Min Act: -0.1700
Data Index: 812438 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7041. Min Range: -2.7041
Max Act: 2.6560. Min Act: -0.1700
Data Index: 2313088 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7041. Min Range: -2.7041
Max Act: 2.6560. Min Act: -0.1700
Data Index: 3954843 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7041. Min Range: -2.7041
Max Act: 2.6400. Min Act: -0.1700
Data Index: 1184106 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7041. Min Range: -2.7041
Max Act: 2.6239. Min Act: -0.1700
Data Index: 7917691 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7041. Min Range: -2.7041
Max Act: 2.5917. Min Act: -0.1700
Data Index: 6635565 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7041. Min Range: -2.7041
Max Act: 2.5756. Min Act: -0.1700
Data Index: 8457700 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7041. Min Range: -2.7041
Max Act: 2.5917. Min Act: -0.1700
Data Index: 3341222 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7041. Min Range: -2.7041
Max Act: 2.5917. Min Act: -0.1700
Data Index: 3657577 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7041. Min Range: -2.7041
Max Act: 2.5756. Min Act: -0.1700
Data Index: 582666 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7041. Min Range: -2.7041
Max Act: 2.5595. Min Act: -0.1700
Data Index: 7379514 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7041. Min Range: -2.7041
Max Act: 2.5756. Min Act: -0.1700
Data Index: 4292778 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7041. Min Range: -2.7041
Max Act: 2.5756. Min Act: -0.1700
Data Index: 5179915 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7041. Min Range: -2.7041
Max Act: 2.5917. Min Act: -0.1700
Data Index: 5621908 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7041. Min Range: -2.7041
Max Act: 2.5917. Min Act: -0.1700
Data Index: 8298727 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #19