Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2141 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7579. Min Range: -7.7579
Max Act: 7.7579. Min Act: -0.1700
Data Index: 5349208 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7579. Min Range: -7.7579
Max Act: 7.6641. Min Act: -0.1700
Data Index: 1639856 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7579. Min Range: -7.7579
Max Act: 7.5391. Min Act: -0.1700
Data Index: 793276 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7579. Min Range: -7.7579
Max Act: 7.5704. Min Act: -0.1700
Data Index: 2560024 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7579. Min Range: -7.7579
Max Act: 7.4766. Min Act: -0.1700
Data Index: 2258322 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7579. Min Range: -7.7579
Max Act: 7.3829. Min Act: -0.1700
Data Index: 3581310 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7579. Min Range: -7.7579
Max Act: 7.4141. Min Act: -0.1700
Data Index: 1951695 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7579. Min Range: -7.7579
Max Act: 7.3204. Min Act: -0.1700
Data Index: 7961689 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7579. Min Range: -7.7579
Max Act: 7.3204. Min Act: -0.1700
Data Index: 6085215 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7579. Min Range: -7.7579
Max Act: 7.3204. Min Act: -0.1700
Data Index: 4138599 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7579. Min Range: -7.7579
Max Act: 7.2891. Min Act: -0.1700
Data Index: 773591 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7579. Min Range: -7.7579
Max Act: 7.2579. Min Act: -0.1700
Data Index: 8388107 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7579. Min Range: -7.7579
Max Act: 7.2579. Min Act: -0.1700
Data Index: 2725790 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7579. Min Range: -7.7579
Max Act: 7.2579. Min Act: -0.1700
Data Index: 4897997 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7579. Min Range: -7.7579
Max Act: 7.2891. Min Act: -0.1700
Data Index: 7062293 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7579. Min Range: -7.7579
Max Act: 7.2579. Min Act: -0.1700
Data Index: 115024 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7579. Min Range: -7.7579
Max Act: 7.1954. Min Act: -0.1700
Data Index: 5083769 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7579. Min Range: -7.7579
Max Act: 7.1954. Min Act: -0.1700
Data Index: 7969387 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7579. Min Range: -7.7579
Max Act: 7.1329. Min Act: -0.1700
Data Index: 1678293 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7579. Min Range: -7.7579
Max Act: 7.1641. Min Act: -0.1700
Data Index: 3984914 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #19