Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3598 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.1215. Min Range: -5.1215
Max Act: 5.1215. Min Act: -0.1700
Data Index: 2998503 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1215. Min Range: -5.1215
Max Act: 5.0590. Min Act: -0.1700
Data Index: 2839235 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1215. Min Range: -5.1215
Max Act: 4.9652. Min Act: -0.1700
Data Index: 5296463 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1215. Min Range: -5.1215
Max Act: 4.9652. Min Act: -0.1700
Data Index: 1055147 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1215. Min Range: -5.1215
Max Act: 4.9340. Min Act: -0.1700
Data Index: 7542742 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1215. Min Range: -5.1215
Max Act: 4.9340. Min Act: -0.1700
Data Index: 3400659 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1215. Min Range: -5.1215
Max Act: 4.9340. Min Act: -0.1700
Data Index: 5082354 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1215. Min Range: -5.1215
Max Act: 4.9027. Min Act: -0.1700
Data Index: 4101710 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1215. Min Range: -5.1215
Max Act: 4.9340. Min Act: -0.1700
Data Index: 5327638 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1215. Min Range: -5.1215
Max Act: 4.9027. Min Act: -0.1700
Data Index: 1939795 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1215. Min Range: -5.1215
Max Act: 4.9027. Min Act: -0.1700
Data Index: 6819274 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1215. Min Range: -5.1215
Max Act: 4.8715. Min Act: -0.1700
Data Index: 6498548 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1215. Min Range: -5.1215
Max Act: 4.8715. Min Act: -0.1700
Data Index: 6034937 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1215. Min Range: -5.1215
Max Act: 4.8402. Min Act: -0.1700
Data Index: 1880341 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1215. Min Range: -5.1215
Max Act: 4.8402. Min Act: -0.1700
Data Index: 8692015 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1215. Min Range: -5.1215
Max Act: 4.8090. Min Act: -0.1700
Data Index: 1724600 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1215. Min Range: -5.1215
Max Act: 4.8090. Min Act: -0.1700
Data Index: 2896333 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1215. Min Range: -5.1215
Max Act: 4.7777. Min Act: -0.1700
Data Index: 6550842 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1215. Min Range: -5.1215
Max Act: 4.7777. Min Act: -0.1700
Data Index: 7077405 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1215. Min Range: -5.1215
Max Act: 4.7465. Min Act: -0.1700
Data Index: 433955 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #19