Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4424 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1560. Min Range: -5.1560
Max Act: 5.1560. Min Act: -0.1700
Data Index: 3698234 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1560. Min Range: -5.1560
Max Act: 5.0310. Min Act: -0.1700
Data Index: 7523684 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1560. Min Range: -5.1560
Max Act: 4.9997. Min Act: -0.1700
Data Index: 3907384 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1560. Min Range: -5.1560
Max Act: 4.9685. Min Act: -0.1700
Data Index: 5141493 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1560. Min Range: -5.1560
Max Act: 4.9372. Min Act: -0.1700
Data Index: 8118760 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1560. Min Range: -5.1560
Max Act: 4.9060. Min Act: -0.1700
Data Index: 4965135 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1560. Min Range: -5.1560
Max Act: 4.8747. Min Act: -0.1700
Data Index: 369263 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1560. Min Range: -5.1560
Max Act: 4.8435. Min Act: -0.1700
Data Index: 3874796 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1560. Min Range: -5.1560
Max Act: 4.8435. Min Act: -0.1700
Data Index: 7647778 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1560. Min Range: -5.1560
Max Act: 4.8747. Min Act: -0.1700
Data Index: 6306597 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1560. Min Range: -5.1560
Max Act: 4.8435. Min Act: -0.1700
Data Index: 5270650 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1560. Min Range: -5.1560
Max Act: 4.7810. Min Act: -0.1700
Data Index: 5127928 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1560. Min Range: -5.1560
Max Act: 4.7810. Min Act: -0.1700
Data Index: 730836 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1560. Min Range: -5.1560
Max Act: 4.7810. Min Act: -0.1700
Data Index: 8352213 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1560. Min Range: -5.1560
Max Act: 4.7497. Min Act: -0.1700
Data Index: 7469923 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1560. Min Range: -5.1560
Max Act: 4.7497. Min Act: -0.1700
Data Index: 5049018 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1560. Min Range: -5.1560
Max Act: 4.7185. Min Act: -0.1700
Data Index: 634814 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1560. Min Range: -5.1560
Max Act: 4.7185. Min Act: -0.1700
Data Index: 4432495 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1560. Min Range: -5.1560
Max Act: 4.7185. Min Act: -0.1700
Data Index: 6377906 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1560. Min Range: -5.1560
Max Act: 4.6872. Min Act: -0.1700
Data Index: 6450642 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #19