Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2626 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5931. Min Range: -6.5931
Max Act: 6.5931. Min Act: -0.1700
Data Index: 3728227 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5931. Min Range: -6.5931
Max Act: 6.3744. Min Act: -0.1700
Data Index: 3932529 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5931. Min Range: -6.5931
Max Act: 6.2806. Min Act: -0.1700
Data Index: 6213033 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5931. Min Range: -6.5931
Max Act: 6.3119. Min Act: -0.1700
Data Index: 4009883 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5931. Min Range: -6.5931
Max Act: 6.2494. Min Act: -0.1700
Data Index: 4377244 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5931. Min Range: -6.5931
Max Act: 6.2806. Min Act: -0.1700
Data Index: 7923337 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5931. Min Range: -6.5931
Max Act: 6.2181. Min Act: -0.1700
Data Index: 2631695 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5931. Min Range: -6.5931
Max Act: 6.1244. Min Act: -0.1700
Data Index: 555357 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5931. Min Range: -6.5931
Max Act: 6.0931. Min Act: -0.1700
Data Index: 5615465 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5931. Min Range: -6.5931
Max Act: 6.0931. Min Act: -0.1700
Data Index: 6217636 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5931. Min Range: -6.5931
Max Act: 6.0619. Min Act: -0.1700
Data Index: 6584975 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5931. Min Range: -6.5931
Max Act: 6.0306. Min Act: -0.1700
Data Index: 6274696 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5931. Min Range: -6.5931
Max Act: 6.0306. Min Act: -0.1700
Data Index: 6447179 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5931. Min Range: -6.5931
Max Act: 5.9994. Min Act: -0.1700
Data Index: 7925746 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5931. Min Range: -6.5931
Max Act: 5.9994. Min Act: -0.1700
Data Index: 8499215 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5931. Min Range: -6.5931
Max Act: 5.9994. Min Act: -0.1700
Data Index: 879840 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5931. Min Range: -6.5931
Max Act: 5.9681. Min Act: -0.1700
Data Index: 3091484 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5931. Min Range: -6.5931
Max Act: 5.9681. Min Act: -0.1700
Data Index: 1744399 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5931. Min Range: -6.5931
Max Act: 5.9369. Min Act: -0.1700
Data Index: 5082980 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5931. Min Range: -6.5931
Max Act: 5.9369. Min Act: -0.1700
Data Index: 3001289 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #19