Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3468 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.9403. Min Range: -6.9403
Max Act: 6.9403. Min Act: -0.1700
Data Index: 1039763 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9403. Min Range: -6.9403
Max Act: 6.7840. Min Act: -0.1700
Data Index: 1288212 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9403. Min Range: -6.9403
Max Act: 6.5653. Min Act: -0.1700
Data Index: 2620879 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9403. Min Range: -6.9403
Max Act: 6.5965. Min Act: -0.1700
Data Index: 6510424 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9403. Min Range: -6.9403
Max Act: 6.5653. Min Act: -0.1700
Data Index: 5089154 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9403. Min Range: -6.9403
Max Act: 6.4715. Min Act: -0.1700
Data Index: 2228631 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9403. Min Range: -6.9403
Max Act: 6.3778. Min Act: -0.1700
Data Index: 679 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9403. Min Range: -6.9403
Max Act: 6.4090. Min Act: -0.1700
Data Index: 8158019 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9403. Min Range: -6.9403
Max Act: 6.3465. Min Act: -0.1700
Data Index: 5910954 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9403. Min Range: -6.9403
Max Act: 6.3465. Min Act: -0.1700
Data Index: 4738109 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9403. Min Range: -6.9403
Max Act: 6.3465. Min Act: -0.1700
Data Index: 5720728 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9403. Min Range: -6.9403
Max Act: 6.3153. Min Act: -0.1700
Data Index: 7374167 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9403. Min Range: -6.9403
Max Act: 6.2840. Min Act: -0.1700
Data Index: 7485031 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9403. Min Range: -6.9403
Max Act: 6.2840. Min Act: -0.1700
Data Index: 3728139 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9403. Min Range: -6.9403
Max Act: 6.3153. Min Act: -0.1700
Data Index: 6075110 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9403. Min Range: -6.9403
Max Act: 6.2528. Min Act: -0.1700
Data Index: 4312588 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9403. Min Range: -6.9403
Max Act: 6.2840. Min Act: -0.1700
Data Index: 8479097 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9403. Min Range: -6.9403
Max Act: 6.2840. Min Act: -0.1700
Data Index: 6833488 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9403. Min Range: -6.9403
Max Act: 6.2840. Min Act: -0.1700
Data Index: 5256716 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9403. Min Range: -6.9403
Max Act: 6.2215. Min Act: -0.1700
Data Index: 5839194 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #19