Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6397 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.2875. Min Range: -4.2875
Max Act: 4.2875. Min Act: -0.1700
Data Index: 2336796 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2875. Min Range: -4.2875
Max Act: 4.2563. Min Act: -0.1700
Data Index: 4518332 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2875. Min Range: -4.2875
Max Act: 4.2250. Min Act: -0.1700
Data Index: 7157839 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2875. Min Range: -4.2875
Max Act: 4.1938. Min Act: -0.1699
Data Index: 7159312 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2875. Min Range: -4.2875
Max Act: 4.1938. Min Act: -0.1700
Data Index: 3805220 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2875. Min Range: -4.2875
Max Act: 4.1625. Min Act: -0.1700
Data Index: 5127192 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2875. Min Range: -4.2875
Max Act: 4.0688. Min Act: -0.1700
Data Index: 2006761 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2875. Min Range: -4.2875
Max Act: 4.0375. Min Act: -0.1700
Data Index: 7419507 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2875. Min Range: -4.2875
Max Act: 4.0375. Min Act: -0.1700
Data Index: 427245 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2875. Min Range: -4.2875
Max Act: 4.0375. Min Act: -0.1700
Data Index: 6052235 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2875. Min Range: -4.2875
Max Act: 4.0062. Min Act: -0.1700
Data Index: 729029 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2875. Min Range: -4.2875
Max Act: 3.9750. Min Act: -0.1700
Data Index: 1161605 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2875. Min Range: -4.2875
Max Act: 3.9750. Min Act: -0.1700
Data Index: 4564597 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2875. Min Range: -4.2875
Max Act: 3.9750. Min Act: -0.1700
Data Index: 3452354 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2875. Min Range: -4.2875
Max Act: 3.9437. Min Act: -0.1700
Data Index: 3499228 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2875. Min Range: -4.2875
Max Act: 3.9437. Min Act: -0.1700
Data Index: 667705 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2875. Min Range: -4.2875
Max Act: 3.9124. Min Act: -0.1700
Data Index: 8773504 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2875. Min Range: -4.2875
Max Act: 3.9124. Min Act: -0.1700
Data Index: 5033990 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2875. Min Range: -4.2875
Max Act: 3.9124. Min Act: -0.1700
Data Index: 624641 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2875. Min Range: -4.2875
Max Act: 3.8812. Min Act: -0.1700
Data Index: 4717662 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #19