Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4203 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5135. Min Range: -5.5135
Max Act: 5.5135. Min Act: -0.1700
Data Index: 8662693 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5135. Min Range: -5.5135
Max Act: 5.3885. Min Act: -0.1700
Data Index: 5898821 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5135. Min Range: -5.5135
Max Act: 5.2635. Min Act: -0.1700
Data Index: 272129 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5135. Min Range: -5.5135
Max Act: 5.2948. Min Act: -0.1700
Data Index: 8639640 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5135. Min Range: -5.5135
Max Act: 5.2948. Min Act: -0.1700
Data Index: 4947776 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5135. Min Range: -5.5135
Max Act: 5.2635. Min Act: -0.1700
Data Index: 5781132 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5135. Min Range: -5.5135
Max Act: 5.2323. Min Act: -0.1700
Data Index: 3238977 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5135. Min Range: -5.5135
Max Act: 5.2010. Min Act: -0.1700
Data Index: 872627 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5135. Min Range: -5.5135
Max Act: 5.2010. Min Act: -0.1700
Data Index: 706595 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5135. Min Range: -5.5135
Max Act: 5.1698. Min Act: -0.1700
Data Index: 753037 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5135. Min Range: -5.5135
Max Act: 5.1385. Min Act: -0.1700
Data Index: 5310368 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5135. Min Range: -5.5135
Max Act: 5.1385. Min Act: -0.1700
Data Index: 5977099 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5135. Min Range: -5.5135
Max Act: 5.1385. Min Act: -0.1700
Data Index: 5171641 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5135. Min Range: -5.5135
Max Act: 5.1385. Min Act: -0.1700
Data Index: 5595480 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5135. Min Range: -5.5135
Max Act: 5.1073. Min Act: -0.1700
Data Index: 6718497 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5135. Min Range: -5.5135
Max Act: 5.1073. Min Act: -0.1700
Data Index: 721489 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5135. Min Range: -5.5135
Max Act: 5.1073. Min Act: -0.1700
Data Index: 568146 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5135. Min Range: -5.5135
Max Act: 5.1073. Min Act: -0.1700
Data Index: 2879703 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5135. Min Range: -5.5135
Max Act: 5.1073. Min Act: -0.1700
Data Index: 5626691 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5135. Min Range: -5.5135
Max Act: 5.0760. Min Act: -0.1700
Data Index: 5668947 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #19