Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2248 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.0178. Min Range: -3.0178
Max Act: 3.0178. Min Act: -0.1700
Data Index: 4447082 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0178. Min Range: -3.0178
Max Act: 3.0178. Min Act: -0.1700
Data Index: 6667029 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0178. Min Range: -3.0178
Max Act: 3.0178. Min Act: -0.1700
Data Index: 6424157 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0178. Min Range: -3.0178
Max Act: 3.0178. Min Act: -0.1700
Data Index: 6382 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0178. Min Range: -3.0178
Max Act: 3.0178. Min Act: -0.1700
Data Index: 4487701 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0178. Min Range: -3.0178
Max Act: 3.0178. Min Act: -0.1700
Data Index: 2997910 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0178. Min Range: -3.0178
Max Act: 3.0178. Min Act: -0.1700
Data Index: 4525013 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0178. Min Range: -3.0178
Max Act: 3.0178. Min Act: -0.1700
Data Index: 5481630 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0178. Min Range: -3.0178
Max Act: 3.0178. Min Act: -0.1700
Data Index: 445634 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0178. Min Range: -3.0178
Max Act: 2.9862. Min Act: -0.1700
Data Index: 6833527 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0178. Min Range: -3.0178
Max Act: 2.9862. Min Act: -0.1700
Data Index: 654844 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0178. Min Range: -3.0178
Max Act: 2.9862. Min Act: -0.1700
Data Index: 6250766 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0178. Min Range: -3.0178
Max Act: 2.9862. Min Act: -0.1700
Data Index: 6209832 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0178. Min Range: -3.0178
Max Act: 2.9862. Min Act: -0.1700
Data Index: 5786925 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0178. Min Range: -3.0178
Max Act: 2.9862. Min Act: -0.1700
Data Index: 4889668 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0178. Min Range: -3.0178
Max Act: 2.9862. Min Act: -0.1700
Data Index: 223879 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0178. Min Range: -3.0178
Max Act: 2.9862. Min Act: -0.1700
Data Index: 2831896 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0178. Min Range: -3.0178
Max Act: 2.9862. Min Act: -0.1700
Data Index: 2280988 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0178. Min Range: -3.0178
Max Act: 2.9862. Min Act: -0.1700
Data Index: 4483063 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0178. Min Range: -3.0178
Max Act: 2.9862. Min Act: -0.1700
Data Index: 1631927 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #19