Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2922 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7036. Min Range: -5.7036
Max Act: 5.7036. Min Act: -0.1700
Data Index: 1438826 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7036. Min Range: -5.7036
Max Act: 5.6723. Min Act: -0.1700
Data Index: 5458267 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7036. Min Range: -5.7036
Max Act: 5.6723. Min Act: -0.1700
Data Index: 8462764 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7036. Min Range: -5.7036
Max Act: 5.6411. Min Act: -0.1700
Data Index: 6113744 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7036. Min Range: -5.7036
Max Act: 5.6411. Min Act: -0.1700
Data Index: 7556243 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7036. Min Range: -5.7036
Max Act: 5.6098. Min Act: -0.1700
Data Index: 4298374 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7036. Min Range: -5.7036
Max Act: 5.5786. Min Act: -0.1700
Data Index: 1825134 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7036. Min Range: -5.7036
Max Act: 5.5786. Min Act: -0.1700
Data Index: 4578010 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7036. Min Range: -5.7036
Max Act: 5.5161. Min Act: -0.1700
Data Index: 4998948 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7036. Min Range: -5.7036
Max Act: 5.5161. Min Act: -0.1700
Data Index: 4976108 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7036. Min Range: -5.7036
Max Act: 5.5161. Min Act: -0.1700
Data Index: 76151 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7036. Min Range: -5.7036
Max Act: 5.5161. Min Act: -0.1700
Data Index: 8613024 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7036. Min Range: -5.7036
Max Act: 5.4848. Min Act: -0.1700
Data Index: 1977827 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7036. Min Range: -5.7036
Max Act: 5.4848. Min Act: -0.1700
Data Index: 5971720 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7036. Min Range: -5.7036
Max Act: 5.4848. Min Act: -0.1700
Data Index: 7530927 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7036. Min Range: -5.7036
Max Act: 5.4536. Min Act: -0.1700
Data Index: 5503423 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7036. Min Range: -5.7036
Max Act: 5.4223. Min Act: -0.1700
Data Index: 6576670 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7036. Min Range: -5.7036
Max Act: 5.4223. Min Act: -0.1700
Data Index: 3268958 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7036. Min Range: -5.7036
Max Act: 5.3911. Min Act: -0.1700
Data Index: 6476462 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7036. Min Range: -5.7036
Max Act: 5.3911. Min Act: -0.1700
Data Index: 7404459 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #19