Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3837 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.1852. Min Range: -6.1852
Max Act: 6.1852. Min Act: -0.1700
Data Index: 456151 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1852. Min Range: -6.1852
Max Act: 6.1540. Min Act: -0.1700
Data Index: 5819631 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1852. Min Range: -6.1852
Max Act: 6.1227. Min Act: -0.1700
Data Index: 6208195 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1852. Min Range: -6.1852
Max Act: 6.0290. Min Act: -0.1700
Data Index: 6113715 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1852. Min Range: -6.1852
Max Act: 6.0290. Min Act: -0.1700
Data Index: 589365 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1852. Min Range: -6.1852
Max Act: 5.9977. Min Act: -0.1700
Data Index: 4827637 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1852. Min Range: -6.1852
Max Act: 5.9665. Min Act: -0.1700
Data Index: 5393558 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1852. Min Range: -6.1852
Max Act: 5.9665. Min Act: -0.1700
Data Index: 7218596 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1852. Min Range: -6.1852
Max Act: 5.9352. Min Act: -0.1700
Data Index: 7475441 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1852. Min Range: -6.1852
Max Act: 5.9352. Min Act: -0.1700
Data Index: 7375974 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1852. Min Range: -6.1852
Max Act: 5.9040. Min Act: -0.1700
Data Index: 1975849 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1852. Min Range: -6.1852
Max Act: 5.9040. Min Act: -0.1700
Data Index: 4233010 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1852. Min Range: -6.1852
Max Act: 5.8727. Min Act: -0.1700
Data Index: 8664806 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1852. Min Range: -6.1852
Max Act: 5.9040. Min Act: -0.1700
Data Index: 6316815 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1852. Min Range: -6.1852
Max Act: 5.8727. Min Act: -0.1700
Data Index: 2210465 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1852. Min Range: -6.1852
Max Act: 5.8727. Min Act: -0.1700
Data Index: 1963194 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1852. Min Range: -6.1852
Max Act: 5.8415. Min Act: -0.1700
Data Index: 3857282 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1852. Min Range: -6.1852
Max Act: 5.8415. Min Act: -0.1700
Data Index: 6810086 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1852. Min Range: -6.1852
Max Act: 5.8415. Min Act: -0.1700
Data Index: 6321709 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1852. Min Range: -6.1852
Max Act: 5.8415. Min Act: -0.1700
Data Index: 4306307 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #19