Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2382 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.9521. Min Range: -2.9521
Max Act: 2.9521. Min Act: -0.1221
Data Index: 954797 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9521. Min Range: -2.9521
Max Act: 2.8093. Min Act: -0.1500
Data Index: 1188372 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9521. Min Range: -2.9521
Max Act: 2.7933. Min Act: -0.0932
Data Index: 6262194 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9521. Min Range: -2.9521
Max Act: 2.7774. Min Act: -0.1230
Data Index: 7968274 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9521. Min Range: -2.9521
Max Act: 2.7135. Min Act: -0.0773
Data Index: 8075122 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9521. Min Range: -2.9521
Max Act: 2.7135. Min Act: -0.1414
Data Index: 7256613 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9521. Min Range: -2.9521
Max Act: 2.6815. Min Act: -0.1696
Data Index: 23059 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9521. Min Range: -2.9521
Max Act: 2.7135. Min Act: -0.1615
Data Index: 5483929 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9521. Min Range: -2.9521
Max Act: 2.7295. Min Act: -0.1487
Data Index: 2585762 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9521. Min Range: -2.9521
Max Act: 2.6975. Min Act: -0.1442
Data Index: 1307826 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9521. Min Range: -2.9521
Max Act: 2.6815. Min Act: -0.1681
Data Index: 8374943 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9521. Min Range: -2.9521
Max Act: 2.6975. Min Act: -0.1500
Data Index: 3015002 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9521. Min Range: -2.9521
Max Act: 2.6975. Min Act: -0.1622
Data Index: 1196189 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9521. Min Range: -2.9521
Max Act: 2.6655. Min Act: -0.1201
Data Index: 8306773 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9521. Min Range: -2.9521
Max Act: 2.6975. Min Act: -0.1517
Data Index: 4477292 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9521. Min Range: -2.9521
Max Act: 2.6815. Min Act: -0.1377
Data Index: 231029 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9521. Min Range: -2.9521
Max Act: 2.6815. Min Act: -0.1303
Data Index: 7189133 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9521. Min Range: -2.9521
Max Act: 2.6655. Min Act: -0.1249
Data Index: 4791741 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9521. Min Range: -2.9521
Max Act: 2.6495. Min Act: -0.1539
Data Index: 6591035 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9521. Min Range: -2.9521
Max Act: 2.6495. Min Act: -0.1699
Data Index: 1113437 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #19