Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3900 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.6466. Min Range: -9.6466
Max Act: 9.6466. Min Act: -0.1700
Data Index: 4337051 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.6466. Min Range: -9.6466
Max Act: 9.3341. Min Act: -0.1700
Data Index: 3711399 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.6466. Min Range: -9.6466
Max Act: 9.2091. Min Act: -0.1700
Data Index: 744573 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.6466. Min Range: -9.6466
Max Act: 9.2091. Min Act: -0.1700
Data Index: 7649747 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.6466. Min Range: -9.6466
Max Act: 9.1466. Min Act: -0.1700
Data Index: 2009640 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.6466. Min Range: -9.6466
Max Act: 9.1466. Min Act: -0.1700
Data Index: 5958584 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.6466. Min Range: -9.6466
Max Act: 9.0841. Min Act: -0.1700
Data Index: 7939088 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.6466. Min Range: -9.6466
Max Act: 9.1466. Min Act: -0.1700
Data Index: 3193642 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.6466. Min Range: -9.6466
Max Act: 9.0841. Min Act: -0.1700
Data Index: 5529495 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.6466. Min Range: -9.6466
Max Act: 9.0841. Min Act: -0.1700
Data Index: 6470142 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.6466. Min Range: -9.6466
Max Act: 9.0841. Min Act: -0.1700
Data Index: 4517233 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.6466. Min Range: -9.6466
Max Act: 9.0841. Min Act: -0.1700
Data Index: 3399306 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.6466. Min Range: -9.6466
Max Act: 9.0216. Min Act: -0.1700
Data Index: 5048300 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.6466. Min Range: -9.6466
Max Act: 9.0216. Min Act: -0.1700
Data Index: 5934513 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.6466. Min Range: -9.6466
Max Act: 9.0216. Min Act: -0.1700
Data Index: 597730 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.6466. Min Range: -9.6466
Max Act: 9.0216. Min Act: -0.1700
Data Index: 6482807 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.6466. Min Range: -9.6466
Max Act: 8.9591. Min Act: -0.1700
Data Index: 8181210 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.6466. Min Range: -9.6466
Max Act: 8.9591. Min Act: -0.1700
Data Index: 2922202 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.6466. Min Range: -9.6466
Max Act: 8.9591. Min Act: -0.1700
Data Index: 7047745 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.6466. Min Range: -9.6466
Max Act: 8.9591. Min Act: -0.1700
Data Index: 5697836 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #19