Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5705 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8152. Min Range: -4.8152
Max Act: 4.8152. Min Act: -0.1700
Data Index: 907944 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8152. Min Range: -4.8152
Max Act: 4.6902. Min Act: -0.1700
Data Index: 5942032 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8152. Min Range: -4.8152
Max Act: 4.6589. Min Act: -0.1700
Data Index: 369111 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8152. Min Range: -4.8152
Max Act: 4.6277. Min Act: -0.1700
Data Index: 791778 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8152. Min Range: -4.8152
Max Act: 4.5964. Min Act: -0.1700
Data Index: 2371222 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8152. Min Range: -4.8152
Max Act: 4.5964. Min Act: -0.1700
Data Index: 43721 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8152. Min Range: -4.8152
Max Act: 4.5964. Min Act: -0.1700
Data Index: 7953270 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8152. Min Range: -4.8152
Max Act: 4.5964. Min Act: -0.1700
Data Index: 2077805 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8152. Min Range: -4.8152
Max Act: 4.5339. Min Act: -0.1700
Data Index: 4207873 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8152. Min Range: -4.8152
Max Act: 4.5339. Min Act: -0.1700
Data Index: 907942 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8152. Min Range: -4.8152
Max Act: 4.5027. Min Act: -0.1700
Data Index: 6842501 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8152. Min Range: -4.8152
Max Act: 4.5027. Min Act: -0.1700
Data Index: 7137491 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8152. Min Range: -4.8152
Max Act: 4.5027. Min Act: -0.1700
Data Index: 2030424 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8152. Min Range: -4.8152
Max Act: 4.5339. Min Act: -0.1700
Data Index: 6248692 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8152. Min Range: -4.8152
Max Act: 4.5027. Min Act: -0.1700
Data Index: 1328506 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8152. Min Range: -4.8152
Max Act: 4.4714. Min Act: -0.1700
Data Index: 2938939 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8152. Min Range: -4.8152
Max Act: 4.4714. Min Act: -0.1700
Data Index: 907943 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8152. Min Range: -4.8152
Max Act: 4.4714. Min Act: -0.1700
Data Index: 294668 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8152. Min Range: -4.8152
Max Act: 4.4714. Min Act: -0.1700
Data Index: 2765908 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8152. Min Range: -4.8152
Max Act: 4.4402. Min Act: -0.1700
Data Index: 2668941 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #19