Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3578 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2164. Min Range: -6.2164
Max Act: 6.2164. Min Act: -0.1700
Data Index: 7106347 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2164. Min Range: -6.2164
Max Act: 6.1852. Min Act: -0.1700
Data Index: 4882621 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2164. Min Range: -6.2164
Max Act: 6.0914. Min Act: -0.1700
Data Index: 7106349 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2164. Min Range: -6.2164
Max Act: 5.9977. Min Act: -0.1700
Data Index: 7232099 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2164. Min Range: -6.2164
Max Act: 5.9977. Min Act: -0.1700
Data Index: 4980294 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2164. Min Range: -6.2164
Max Act: 5.9664. Min Act: -0.1700
Data Index: 8177754 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2164. Min Range: -6.2164
Max Act: 5.9039. Min Act: -0.1700
Data Index: 916931 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2164. Min Range: -6.2164
Max Act: 5.9039. Min Act: -0.1700
Data Index: 4036669 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2164. Min Range: -6.2164
Max Act: 5.8102. Min Act: -0.1700
Data Index: 444579 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2164. Min Range: -6.2164
Max Act: 5.7477. Min Act: -0.1700
Data Index: 2897213 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2164. Min Range: -6.2164
Max Act: 5.7164. Min Act: -0.1700
Data Index: 8022156 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2164. Min Range: -6.2164
Max Act: 5.7477. Min Act: -0.1700
Data Index: 4949650 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2164. Min Range: -6.2164
Max Act: 5.6852. Min Act: -0.1700
Data Index: 2917252 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2164. Min Range: -6.2164
Max Act: 5.6539. Min Act: -0.1700
Data Index: 418296 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2164. Min Range: -6.2164
Max Act: 5.6539. Min Act: -0.1700
Data Index: 6705131 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2164. Min Range: -6.2164
Max Act: 5.6227. Min Act: -0.1700
Data Index: 4395612 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2164. Min Range: -6.2164
Max Act: 5.6227. Min Act: -0.1700
Data Index: 7183540 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2164. Min Range: -6.2164
Max Act: 5.6227. Min Act: -0.1700
Data Index: 5793428 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2164. Min Range: -6.2164
Max Act: 5.5914. Min Act: -0.1700
Data Index: 3386142 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2164. Min Range: -6.2164
Max Act: 5.6227. Min Act: -0.1700
Data Index: 6025932 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #19