Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5990 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4480. Min Range: -8.4480
Max Act: 8.4480. Min Act: -0.1700
Data Index: 5734155 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4480. Min Range: -8.4480
Max Act: 8.3230. Min Act: -0.1700
Data Index: 4755295 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4480. Min Range: -8.4480
Max Act: 8.0730. Min Act: -0.1700
Data Index: 3790713 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4480. Min Range: -8.4480
Max Act: 7.9168. Min Act: -0.1700
Data Index: 1057246 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4480. Min Range: -8.4480
Max Act: 7.7605. Min Act: -0.1700
Data Index: 7220518 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4480. Min Range: -8.4480
Max Act: 7.7293. Min Act: -0.1700
Data Index: 4012131 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4480. Min Range: -8.4480
Max Act: 7.6980. Min Act: -0.1700
Data Index: 6460089 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4480. Min Range: -8.4480
Max Act: 7.6668. Min Act: -0.1700
Data Index: 5501623 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4480. Min Range: -8.4480
Max Act: 7.6043. Min Act: -0.1700
Data Index: 4152716 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4480. Min Range: -8.4480
Max Act: 7.6355. Min Act: -0.1700
Data Index: 4164809 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4480. Min Range: -8.4480
Max Act: 7.5730. Min Act: -0.1700
Data Index: 2869640 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4480. Min Range: -8.4480
Max Act: 7.5730. Min Act: -0.1700
Data Index: 7429370 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4480. Min Range: -8.4480
Max Act: 7.6043. Min Act: -0.1700
Data Index: 8608548 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4480. Min Range: -8.4480
Max Act: 7.5418. Min Act: -0.1700
Data Index: 1227559 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4480. Min Range: -8.4480
Max Act: 7.5418. Min Act: -0.1700
Data Index: 6120469 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4480. Min Range: -8.4480
Max Act: 7.4793. Min Act: -0.1700
Data Index: 4919296 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4480. Min Range: -8.4480
Max Act: 7.4793. Min Act: -0.1700
Data Index: 4296482 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4480. Min Range: -8.4480
Max Act: 7.4793. Min Act: -0.1700
Data Index: 8438542 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4480. Min Range: -8.4480
Max Act: 7.4793. Min Act: -0.1700
Data Index: 6800137 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4480. Min Range: -8.4480
Max Act: 7.4168. Min Act: -0.1700
Data Index: 1007517 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #19