Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 643 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.9500. Min Range: -2.9500
Max Act: 2.9500. Min Act: -0.1700
Data Index: 2139945 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9500. Min Range: -2.9500
Max Act: 2.9341. Min Act: -0.1699
Data Index: 646492 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9500. Min Range: -2.9500
Max Act: 2.9341. Min Act: -0.1700
Data Index: 102531 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9500. Min Range: -2.9500
Max Act: 2.9024. Min Act: -0.1700
Data Index: 2444765 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9500. Min Range: -2.9500
Max Act: 2.9024. Min Act: -0.1698
Data Index: 522278 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9500. Min Range: -2.9500
Max Act: 2.9024. Min Act: -0.1700
Data Index: 6059399 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9500. Min Range: -2.9500
Max Act: 2.8866. Min Act: -0.1696
Data Index: 8508261 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9500. Min Range: -2.9500
Max Act: 2.8866. Min Act: -0.1700
Data Index: 7659363 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9500. Min Range: -2.9500
Max Act: 2.8866. Min Act: -0.1700
Data Index: 8143231 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9500. Min Range: -2.9500
Max Act: 2.8548. Min Act: -0.1697
Data Index: 680943 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9500. Min Range: -2.9500
Max Act: 2.8548. Min Act: -0.1699
Data Index: 7815238 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9500. Min Range: -2.9500
Max Act: 2.8230. Min Act: -0.1700
Data Index: 5189936 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9500. Min Range: -2.9500
Max Act: 2.8389. Min Act: -0.1700
Data Index: 7161341 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9500. Min Range: -2.9500
Max Act: 2.8389. Min Act: -0.1699
Data Index: 226321 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9500. Min Range: -2.9500
Max Act: 2.8230. Min Act: -0.1700
Data Index: 8688072 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9500. Min Range: -2.9500
Max Act: 2.8230. Min Act: -0.1700
Data Index: 4214852 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9500. Min Range: -2.9500
Max Act: 2.8230. Min Act: -0.1700
Data Index: 6589736 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9500. Min Range: -2.9500
Max Act: 2.7912. Min Act: -0.1700
Data Index: 3555184 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9500. Min Range: -2.9500
Max Act: 2.8071. Min Act: -0.1698
Data Index: 3610185 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9500. Min Range: -2.9500
Max Act: 2.7912. Min Act: -0.1700
Data Index: 5990782 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #19