Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4008 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.0106. Min Range: -6.0106
Max Act: 6.0106. Min Act: -0.1700
Data Index: 2439745 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0106. Min Range: -6.0106
Max Act: 5.9481. Min Act: -0.1700
Data Index: 5453395 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0106. Min Range: -6.0106
Max Act: 5.8543. Min Act: -0.1700
Data Index: 6553457 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0106. Min Range: -6.0106
Max Act: 5.8543. Min Act: -0.1700
Data Index: 981934 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0106. Min Range: -6.0106
Max Act: 5.7918. Min Act: -0.1700
Data Index: 8327946 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0106. Min Range: -6.0106
Max Act: 5.6981. Min Act: -0.1700
Data Index: 1405223 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0106. Min Range: -6.0106
Max Act: 5.6981. Min Act: -0.1700
Data Index: 322713 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0106. Min Range: -6.0106
Max Act: 5.6668. Min Act: -0.1700
Data Index: 6150009 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0106. Min Range: -6.0106
Max Act: 5.6668. Min Act: -0.1700
Data Index: 3630655 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0106. Min Range: -6.0106
Max Act: 5.6356. Min Act: -0.1700
Data Index: 5882924 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0106. Min Range: -6.0106
Max Act: 5.6356. Min Act: -0.1700
Data Index: 6997288 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0106. Min Range: -6.0106
Max Act: 5.6043. Min Act: -0.1700
Data Index: 6965706 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0106. Min Range: -6.0106
Max Act: 5.5731. Min Act: -0.1700
Data Index: 8179626 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0106. Min Range: -6.0106
Max Act: 5.6043. Min Act: -0.1700
Data Index: 4916816 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0106. Min Range: -6.0106
Max Act: 5.5418. Min Act: -0.1700
Data Index: 1871253 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0106. Min Range: -6.0106
Max Act: 5.5418. Min Act: -0.1700
Data Index: 6451961 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0106. Min Range: -6.0106
Max Act: 5.5106. Min Act: -0.1700
Data Index: 3770299 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0106. Min Range: -6.0106
Max Act: 5.5418. Min Act: -0.1700
Data Index: 7350663 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0106. Min Range: -6.0106
Max Act: 5.5731. Min Act: -0.1700
Data Index: 4505369 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0106. Min Range: -6.0106
Max Act: 5.5106. Min Act: -0.1700
Data Index: 8074437 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #19