Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5806 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3720. Min Range: -5.3720
Max Act: 5.3720. Min Act: -0.1700
Data Index: 7245364 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3720. Min Range: -5.3720
Max Act: 5.3095. Min Act: -0.1700
Data Index: 4907421 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3720. Min Range: -5.3720
Max Act: 5.3095. Min Act: -0.1700
Data Index: 8682191 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3720. Min Range: -5.3720
Max Act: 5.2783. Min Act: -0.1700
Data Index: 8643605 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3720. Min Range: -5.3720
Max Act: 5.2158. Min Act: -0.1700
Data Index: 5765560 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3720. Min Range: -5.3720
Max Act: 5.2158. Min Act: -0.1700
Data Index: 3575011 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3720. Min Range: -5.3720
Max Act: 5.2158. Min Act: -0.1700
Data Index: 1415457 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3720. Min Range: -5.3720
Max Act: 5.2158. Min Act: -0.1700
Data Index: 1387713 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3720. Min Range: -5.3720
Max Act: 5.1845. Min Act: -0.1700
Data Index: 2231782 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3720. Min Range: -5.3720
Max Act: 5.1533. Min Act: -0.1700
Data Index: 6115054 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3720. Min Range: -5.3720
Max Act: 5.1220. Min Act: -0.1700
Data Index: 2201021 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3720. Min Range: -5.3720
Max Act: 5.0908. Min Act: -0.1700
Data Index: 5262672 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3720. Min Range: -5.3720
Max Act: 5.0908. Min Act: -0.1700
Data Index: 1194371 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3720. Min Range: -5.3720
Max Act: 5.0908. Min Act: -0.1700
Data Index: 1131844 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3720. Min Range: -5.3720
Max Act: 5.0908. Min Act: -0.1700
Data Index: 6928667 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3720. Min Range: -5.3720
Max Act: 5.0595. Min Act: -0.1700
Data Index: 5148039 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3720. Min Range: -5.3720
Max Act: 5.0595. Min Act: -0.1700
Data Index: 2155952 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3720. Min Range: -5.3720
Max Act: 5.0595. Min Act: -0.1700
Data Index: 1181351 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3720. Min Range: -5.3720
Max Act: 5.0283. Min Act: -0.1700
Data Index: 5716791 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3720. Min Range: -5.3720
Max Act: 5.0283. Min Act: -0.1700
Data Index: 1716262 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #19