Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1093 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.6798. Min Range: -2.6798
Max Act: 2.6798. Min Act: -0.1700
Data Index: 2206612 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6798. Min Range: -2.6798
Max Act: 2.5673. Min Act: -0.1700
Data Index: 4709362 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6798. Min Range: -2.6798
Max Act: 2.5673. Min Act: -0.1700
Data Index: 2859046 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6798. Min Range: -2.6798
Max Act: 2.5673. Min Act: -0.1700
Data Index: 1133402 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6798. Min Range: -2.6798
Max Act: 2.5511. Min Act: -0.1700
Data Index: 5632390 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6798. Min Range: -2.6798
Max Act: 2.5350. Min Act: -0.1700
Data Index: 8233338 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6798. Min Range: -2.6798
Max Act: 2.4864. Min Act: -0.1700
Data Index: 1510156 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6798. Min Range: -2.6798
Max Act: 2.4702. Min Act: -0.1700
Data Index: 6376970 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6798. Min Range: -2.6798
Max Act: 2.4214. Min Act: -0.1700
Data Index: 1049012 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6798. Min Range: -2.6798
Max Act: 2.4377. Min Act: -0.1700
Data Index: 6143311 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6798. Min Range: -2.6798
Max Act: 2.4214. Min Act: -0.1700
Data Index: 7105030 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6798. Min Range: -2.6798
Max Act: 2.4214. Min Act: -0.1700
Data Index: 2753579 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6798. Min Range: -2.6798
Max Act: 2.4214. Min Act: -0.1700
Data Index: 7953335 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6798. Min Range: -2.6798
Max Act: 2.4051. Min Act: -0.1700
Data Index: 5424400 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6798. Min Range: -2.6798
Max Act: 2.4051. Min Act: -0.1698
Data Index: 6589775 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6798. Min Range: -2.6798
Max Act: 2.4051. Min Act: -0.1700
Data Index: 8087928 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6798. Min Range: -2.6798
Max Act: 2.3888. Min Act: -0.1700
Data Index: 7105031 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6798. Min Range: -2.6798
Max Act: 2.3888. Min Act: -0.1700
Data Index: 7226121 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6798. Min Range: -2.6798
Max Act: 2.3888. Min Act: -0.1700
Data Index: 5893082 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6798. Min Range: -2.6798
Max Act: 2.3724. Min Act: -0.1700
Data Index: 3050411 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #19