Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1750 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.0650. Min Range: -6.0650
Max Act: 6.0650. Min Act: -0.1700
Data Index: 836826 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0650. Min Range: -6.0650
Max Act: 6.0338. Min Act: -0.1700
Data Index: 6137289 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0650. Min Range: -6.0650
Max Act: 6.0025. Min Act: -0.1700
Data Index: 7121065 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0650. Min Range: -6.0650
Max Act: 5.9088. Min Act: -0.1700
Data Index: 5359705 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0650. Min Range: -6.0650
Max Act: 5.9400. Min Act: -0.1700
Data Index: 2494342 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0650. Min Range: -6.0650
Max Act: 5.9713. Min Act: -0.1700
Data Index: 8559541 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0650. Min Range: -6.0650
Max Act: 5.8150. Min Act: -0.1700
Data Index: 2531518 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0650. Min Range: -6.0650
Max Act: 5.8463. Min Act: -0.1700
Data Index: 3351093 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0650. Min Range: -6.0650
Max Act: 5.8150. Min Act: -0.1700
Data Index: 1814656 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0650. Min Range: -6.0650
Max Act: 5.7525. Min Act: -0.1700
Data Index: 782165 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0650. Min Range: -6.0650
Max Act: 5.7525. Min Act: -0.1700
Data Index: 432133 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0650. Min Range: -6.0650
Max Act: 5.7525. Min Act: -0.1700
Data Index: 2088424 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0650. Min Range: -6.0650
Max Act: 5.7213. Min Act: -0.1700
Data Index: 7881928 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0650. Min Range: -6.0650
Max Act: 5.7213. Min Act: -0.1700
Data Index: 4950093 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0650. Min Range: -6.0650
Max Act: 5.7213. Min Act: -0.1700
Data Index: 2123426 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0650. Min Range: -6.0650
Max Act: 5.6900. Min Act: -0.1700
Data Index: 7073286 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0650. Min Range: -6.0650
Max Act: 5.6900. Min Act: -0.1700
Data Index: 2013927 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0650. Min Range: -6.0650
Max Act: 5.6900. Min Act: -0.1700
Data Index: 8008576 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0650. Min Range: -6.0650
Max Act: 5.6900. Min Act: -0.1700
Data Index: 1165329 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0650. Min Range: -6.0650
Max Act: 5.6275. Min Act: -0.1700
Data Index: 7075766 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19