Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2662 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.1104. Min Range: -5.1104
Max Act: 5.1104. Min Act: -0.1700
Data Index: 1998220 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1104. Min Range: -5.1104
Max Act: 5.0791. Min Act: -0.1700
Data Index: 325251 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1104. Min Range: -5.1104
Max Act: 5.0479. Min Act: -0.1700
Data Index: 325250 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1104. Min Range: -5.1104
Max Act: 5.0791. Min Act: -0.1700
Data Index: 6658915 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1104. Min Range: -5.1104
Max Act: 5.0791. Min Act: -0.1700
Data Index: 3758427 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1104. Min Range: -5.1104
Max Act: 5.0791. Min Act: -0.1700
Data Index: 1869465 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1104. Min Range: -5.1104
Max Act: 5.0791. Min Act: -0.1700
Data Index: 4182576 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1104. Min Range: -5.1104
Max Act: 5.0791. Min Act: -0.1700
Data Index: 3495661 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1104. Min Range: -5.1104
Max Act: 4.9229. Min Act: -0.1700
Data Index: 2705915 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1104. Min Range: -5.1104
Max Act: 4.9229. Min Act: -0.1700
Data Index: 4574577 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1104. Min Range: -5.1104
Max Act: 4.8291. Min Act: -0.1700
Data Index: 6384150 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1104. Min Range: -5.1104
Max Act: 4.8291. Min Act: -0.1700
Data Index: 4584583 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1104. Min Range: -5.1104
Max Act: 4.7666. Min Act: -0.1700
Data Index: 6043291 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1104. Min Range: -5.1104
Max Act: 4.7666. Min Act: -0.1700
Data Index: 3686471 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1104. Min Range: -5.1104
Max Act: 4.7354. Min Act: -0.1700
Data Index: 3244874 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1104. Min Range: -5.1104
Max Act: 4.7041. Min Act: -0.1700
Data Index: 1067311 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1104. Min Range: -5.1104
Max Act: 4.7041. Min Act: -0.1700
Data Index: 6598647 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1104. Min Range: -5.1104
Max Act: 4.6416. Min Act: -0.1700
Data Index: 1307402 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1104. Min Range: -5.1104
Max Act: 4.6729. Min Act: -0.1700
Data Index: 3901973 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1104. Min Range: -5.1104
Max Act: 4.5479. Min Act: -0.1700
Data Index: 5215728 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #19