Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3900 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9571. Min Range: -4.9571
Max Act: 4.9571. Min Act: -0.1700
Data Index: 6850943 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9571. Min Range: -4.9571
Max Act: 4.8946. Min Act: -0.1700
Data Index: 1957221 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9571. Min Range: -4.9571
Max Act: 4.9258. Min Act: -0.1700
Data Index: 4109618 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9571. Min Range: -4.9571
Max Act: 4.8008. Min Act: -0.1700
Data Index: 7415416 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9571. Min Range: -4.9571
Max Act: 4.7696. Min Act: -0.1700
Data Index: 1143199 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9571. Min Range: -4.9571
Max Act: 4.8008. Min Act: -0.1700
Data Index: 1384019 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9571. Min Range: -4.9571
Max Act: 4.8008. Min Act: -0.1700
Data Index: 5102155 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9571. Min Range: -4.9571
Max Act: 4.8321. Min Act: -0.1700
Data Index: 2469076 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9571. Min Range: -4.9571
Max Act: 4.7383. Min Act: -0.1700
Data Index: 1796997 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9571. Min Range: -4.9571
Max Act: 4.7696. Min Act: -0.1700
Data Index: 708496 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9571. Min Range: -4.9571
Max Act: 4.7071. Min Act: -0.1700
Data Index: 6794747 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9571. Min Range: -4.9571
Max Act: 4.7071. Min Act: -0.1700
Data Index: 4207680 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9571. Min Range: -4.9571
Max Act: 4.6758. Min Act: -0.1700
Data Index: 2084554 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9571. Min Range: -4.9571
Max Act: 4.6133. Min Act: -0.1700
Data Index: 8417866 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9571. Min Range: -4.9571
Max Act: 4.6446. Min Act: -0.1700
Data Index: 7376303 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9571. Min Range: -4.9571
Max Act: 4.6446. Min Act: -0.1700
Data Index: 843741 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9571. Min Range: -4.9571
Max Act: 4.6133. Min Act: -0.1700
Data Index: 2834345 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9571. Min Range: -4.9571
Max Act: 4.6133. Min Act: -0.1700
Data Index: 2307289 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9571. Min Range: -4.9571
Max Act: 4.6133. Min Act: -0.1700
Data Index: 3539525 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9571. Min Range: -4.9571
Max Act: 4.5821. Min Act: -0.1700
Data Index: 5681474 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #19