Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2707 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.9747. Min Range: -5.9747
Max Act: 5.9747. Min Act: -0.1700
Data Index: 326895 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9747. Min Range: -5.9747
Max Act: 5.9435. Min Act: -0.1700
Data Index: 1408390 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9747. Min Range: -5.9747
Max Act: 5.9122. Min Act: -0.1700
Data Index: 1152133 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9747. Min Range: -5.9747
Max Act: 5.9122. Min Act: -0.1700
Data Index: 1617606 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9747. Min Range: -5.9747
Max Act: 5.7560. Min Act: -0.1700
Data Index: 687184 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9747. Min Range: -5.9747
Max Act: 5.6935. Min Act: -0.1700
Data Index: 5339722 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9747. Min Range: -5.9747
Max Act: 5.5997. Min Act: -0.1700
Data Index: 1375853 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9747. Min Range: -5.9747
Max Act: 5.5372. Min Act: -0.1700
Data Index: 4813171 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9747. Min Range: -5.9747
Max Act: 5.5372. Min Act: -0.1700
Data Index: 2440653 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9747. Min Range: -5.9747
Max Act: 5.5372. Min Act: -0.1700
Data Index: 893527 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9747. Min Range: -5.9747
Max Act: 5.5060. Min Act: -0.1700
Data Index: 7272819 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9747. Min Range: -5.9747
Max Act: 5.4435. Min Act: -0.1700
Data Index: 2079502 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9747. Min Range: -5.9747
Max Act: 5.4747. Min Act: -0.1700
Data Index: 6139134 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9747. Min Range: -5.9747
Max Act: 5.4435. Min Act: -0.1700
Data Index: 1494317 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9747. Min Range: -5.9747
Max Act: 5.4435. Min Act: -0.1700
Data Index: 5505910 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9747. Min Range: -5.9747
Max Act: 5.4747. Min Act: -0.1700
Data Index: 3065286 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9747. Min Range: -5.9747
Max Act: 5.4747. Min Act: -0.1700
Data Index: 2264004 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9747. Min Range: -5.9747
Max Act: 5.4435. Min Act: -0.1700
Data Index: 8670566 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9747. Min Range: -5.9747
Max Act: 5.4435. Min Act: -0.1700
Data Index: 267395 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9747. Min Range: -5.9747
Max Act: 5.4435. Min Act: -0.1700
Data Index: 3339627 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #19