Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2212 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.8396. Min Range: -3.8396
Max Act: 3.8396. Min Act: -0.1700
Data Index: 8695899 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8396. Min Range: -3.8396
Max Act: 3.8084. Min Act: -0.1700
Data Index: 5304228 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8396. Min Range: -3.8396
Max Act: 3.7458. Min Act: -0.1700
Data Index: 2398745 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8396. Min Range: -3.8396
Max Act: 3.6832. Min Act: -0.1700
Data Index: 574341 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8396. Min Range: -3.8396
Max Act: 3.7145. Min Act: -0.1700
Data Index: 99101 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8396. Min Range: -3.8396
Max Act: 3.7145. Min Act: -0.1700
Data Index: 2069210 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8396. Min Range: -3.8396
Max Act: 3.7145. Min Act: -0.1700
Data Index: 7213945 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8396. Min Range: -3.8396
Max Act: 3.6832. Min Act: -0.1700
Data Index: 7992814 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8396. Min Range: -3.8396
Max Act: 3.6832. Min Act: -0.1700
Data Index: 6411901 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8396. Min Range: -3.8396
Max Act: 3.6832. Min Act: -0.1700
Data Index: 90222 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8396. Min Range: -3.8396
Max Act: 3.7145. Min Act: -0.1700
Data Index: 6468171 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8396. Min Range: -3.8396
Max Act: 3.6832. Min Act: -0.1700
Data Index: 2833809 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8396. Min Range: -3.8396
Max Act: 3.6832. Min Act: -0.1700
Data Index: 285803 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8396. Min Range: -3.8396
Max Act: 3.6832. Min Act: -0.1700
Data Index: 2482039 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8396. Min Range: -3.8396
Max Act: 3.6519. Min Act: -0.1700
Data Index: 6157239 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8396. Min Range: -3.8396
Max Act: 3.6519. Min Act: -0.1700
Data Index: 4817940 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8396. Min Range: -3.8396
Max Act: 3.6519. Min Act: -0.1700
Data Index: 800570 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8396. Min Range: -3.8396
Max Act: 3.6832. Min Act: -0.1700
Data Index: 2118226 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8396. Min Range: -3.8396
Max Act: 3.6519. Min Act: -0.1700
Data Index: 1610508 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8396. Min Range: -3.8396
Max Act: 3.6519. Min Act: -0.1700
Data Index: 278209 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #19