Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2086 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.5503. Min Range: -1.5503
Max Act: 1.5503. Min Act: -0.1699
Data Index: 6391936 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.5503. Min Range: -1.5503
Max Act: 1.5416. Min Act: -0.1700
Data Index: 1100182 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.5503. Min Range: -1.5503
Max Act: 1.5503. Min Act: -0.1700
Data Index: 5329158 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.5503. Min Range: -1.5503
Max Act: 1.5241. Min Act: -0.1700
Data Index: 7606260 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.5503. Min Range: -1.5503
Max Act: 1.5241. Min Act: -0.1699
Data Index: 8073861 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.5503. Min Range: -1.5503
Max Act: 1.5153. Min Act: -0.1699
Data Index: 5530898 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.5503. Min Range: -1.5503
Max Act: 1.5065. Min Act: -0.1698
Data Index: 3797242 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.5503. Min Range: -1.5503
Max Act: 1.5065. Min Act: -0.1700
Data Index: 8167115 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.5503. Min Range: -1.5503
Max Act: 1.5065. Min Act: -0.1700
Data Index: 3797249 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.5503. Min Range: -1.5503
Max Act: 1.5065. Min Act: -0.1700
Data Index: 7609119 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.5503. Min Range: -1.5503
Max Act: 1.5065. Min Act: -0.1682
Data Index: 5894744 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.5503. Min Range: -1.5503
Max Act: 1.5065. Min Act: -0.1700
Data Index: 6150714 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.5503. Min Range: -1.5503
Max Act: 1.5065. Min Act: -0.1692
Data Index: 8631907 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.5503. Min Range: -1.5503
Max Act: 1.5065. Min Act: -0.1693
Data Index: 5691044 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.5503. Min Range: -1.5503
Max Act: 1.4977. Min Act: -0.1700
Data Index: 2611416 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.5503. Min Range: -1.5503
Max Act: 1.5065. Min Act: -0.1700
Data Index: 544921 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.5503. Min Range: -1.5503
Max Act: 1.4977. Min Act: -0.1700
Data Index: 3129255 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.5503. Min Range: -1.5503
Max Act: 1.4977. Min Act: -0.1700
Data Index: 3506332 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.5503. Min Range: -1.5503
Max Act: 1.4890. Min Act: -0.1700
Data Index: 8073857 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.5503. Min Range: -1.5503
Max Act: 1.4890. Min Act: -0.1700
Data Index: 4945706 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #19