Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1002 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7329. Min Range: -7.7329
Max Act: 7.7329. Min Act: -0.1700
Data Index: 8446070 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7329. Min Range: -7.7329
Max Act: 7.6391. Min Act: -0.1700
Data Index: 6272320 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7329. Min Range: -7.7329
Max Act: 7.5766. Min Act: -0.1700
Data Index: 2135330 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7329. Min Range: -7.7329
Max Act: 7.3891. Min Act: -0.1700
Data Index: 5223357 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7329. Min Range: -7.7329
Max Act: 7.3579. Min Act: -0.1700
Data Index: 3773522 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7329. Min Range: -7.7329
Max Act: 7.3891. Min Act: -0.1700
Data Index: 5562713 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7329. Min Range: -7.7329
Max Act: 7.3266. Min Act: -0.1700
Data Index: 7616586 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7329. Min Range: -7.7329
Max Act: 7.2641. Min Act: -0.1700
Data Index: 3845395 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7329. Min Range: -7.7329
Max Act: 7.2954. Min Act: -0.1700
Data Index: 1347622 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7329. Min Range: -7.7329
Max Act: 7.1391. Min Act: -0.1700
Data Index: 3114281 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7329. Min Range: -7.7329
Max Act: 7.1391. Min Act: -0.1700
Data Index: 4938587 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7329. Min Range: -7.7329
Max Act: 7.1391. Min Act: -0.1700
Data Index: 4199147 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7329. Min Range: -7.7329
Max Act: 7.1079. Min Act: -0.1700
Data Index: 8042458 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7329. Min Range: -7.7329
Max Act: 7.0766. Min Act: -0.1700
Data Index: 225090 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7329. Min Range: -7.7329
Max Act: 7.0141. Min Act: -0.1700
Data Index: 401455 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7329. Min Range: -7.7329
Max Act: 7.0141. Min Act: -0.1700
Data Index: 7867922 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7329. Min Range: -7.7329
Max Act: 6.9829. Min Act: -0.1700
Data Index: 7119549 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7329. Min Range: -7.7329
Max Act: 6.9829. Min Act: -0.1700
Data Index: 8073118 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7329. Min Range: -7.7329
Max Act: 6.9829. Min Act: -0.1700
Data Index: 6748346 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7329. Min Range: -7.7329
Max Act: 6.9516. Min Act: -0.1700
Data Index: 6995286 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #19