Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1675 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5364. Min Range: -7.5364
Max Act: 7.5364. Min Act: -0.1700
Data Index: 7533587 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5364. Min Range: -7.5364
Max Act: 7.3489. Min Act: -0.1700
Data Index: 5917469 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5364. Min Range: -7.5364
Max Act: 7.3489. Min Act: -0.1700
Data Index: 1616665 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5364. Min Range: -7.5364
Max Act: 7.3801. Min Act: -0.1700
Data Index: 3674155 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5364. Min Range: -7.5364
Max Act: 7.2864. Min Act: -0.1700
Data Index: 8145564 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5364. Min Range: -7.5364
Max Act: 7.1926. Min Act: -0.1700
Data Index: 1368078 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5364. Min Range: -7.5364
Max Act: 7.1926. Min Act: -0.1700
Data Index: 8707615 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5364. Min Range: -7.5364
Max Act: 7.1301. Min Act: -0.1700
Data Index: 2681036 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5364. Min Range: -7.5364
Max Act: 7.0989. Min Act: -0.1700
Data Index: 8610072 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5364. Min Range: -7.5364
Max Act: 7.0989. Min Act: -0.1700
Data Index: 5994762 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5364. Min Range: -7.5364
Max Act: 7.0989. Min Act: -0.1700
Data Index: 3719596 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5364. Min Range: -7.5364
Max Act: 7.0989. Min Act: -0.1700
Data Index: 4756884 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5364. Min Range: -7.5364
Max Act: 7.0989. Min Act: -0.1700
Data Index: 534271 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5364. Min Range: -7.5364
Max Act: 7.0676. Min Act: -0.1700
Data Index: 461405 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5364. Min Range: -7.5364
Max Act: 7.0364. Min Act: -0.1700
Data Index: 3114209 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5364. Min Range: -7.5364
Max Act: 7.0364. Min Act: -0.1700
Data Index: 3650974 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5364. Min Range: -7.5364
Max Act: 7.0364. Min Act: -0.1700
Data Index: 1841871 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5364. Min Range: -7.5364
Max Act: 6.9739. Min Act: -0.1700
Data Index: 5870668 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5364. Min Range: -7.5364
Max Act: 7.0051. Min Act: -0.1700
Data Index: 45817 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5364. Min Range: -7.5364
Max Act: 7.0051. Min Act: -0.1700
Data Index: 6788764 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #19