Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2571 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2185. Min Range: -6.2185
Max Act: 6.2185. Min Act: -0.1700
Data Index: 2001330 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2185. Min Range: -6.2185
Max Act: 6.0935. Min Act: -0.1700
Data Index: 1229153 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2185. Min Range: -6.2185
Max Act: 6.0623. Min Act: -0.1700
Data Index: 2330158 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2185. Min Range: -6.2185
Max Act: 6.0310. Min Act: -0.1700
Data Index: 1499678 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2185. Min Range: -6.2185
Max Act: 6.0310. Min Act: -0.1700
Data Index: 377852 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2185. Min Range: -6.2185
Max Act: 5.9998. Min Act: -0.1700
Data Index: 5939345 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2185. Min Range: -6.2185
Max Act: 5.9998. Min Act: -0.1700
Data Index: 3857210 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2185. Min Range: -6.2185
Max Act: 5.9998. Min Act: -0.1700
Data Index: 4576125 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2185. Min Range: -6.2185
Max Act: 5.9685. Min Act: -0.1700
Data Index: 3815425 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2185. Min Range: -6.2185
Max Act: 5.9685. Min Act: -0.1700
Data Index: 7892338 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2185. Min Range: -6.2185
Max Act: 5.9685. Min Act: -0.1700
Data Index: 3404965 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2185. Min Range: -6.2185
Max Act: 5.9373. Min Act: -0.1700
Data Index: 6703573 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2185. Min Range: -6.2185
Max Act: 5.9373. Min Act: -0.1700
Data Index: 1528057 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2185. Min Range: -6.2185
Max Act: 5.9373. Min Act: -0.1700
Data Index: 5690498 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2185. Min Range: -6.2185
Max Act: 5.9373. Min Act: -0.1700
Data Index: 1037154 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2185. Min Range: -6.2185
Max Act: 5.9060. Min Act: -0.1700
Data Index: 5734453 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2185. Min Range: -6.2185
Max Act: 5.9060. Min Act: -0.1700
Data Index: 8241039 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2185. Min Range: -6.2185
Max Act: 5.9060. Min Act: -0.1700
Data Index: 300588 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2185. Min Range: -6.2185
Max Act: 5.9060. Min Act: -0.1700
Data Index: 711018 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2185. Min Range: -6.2185
Max Act: 5.8748. Min Act: -0.1700
Data Index: 2987373 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #19