Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2122 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8706. Min Range: -7.8706
Max Act: 7.8706. Min Act: -0.1700
Data Index: 1975074 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8706. Min Range: -7.8706
Max Act: 7.4644. Min Act: -0.1700
Data Index: 8262363 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8706. Min Range: -7.8706
Max Act: 7.4019. Min Act: -0.1700
Data Index: 2348106 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8706. Min Range: -7.8706
Max Act: 7.3706. Min Act: -0.1700
Data Index: 4224718 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8706. Min Range: -7.8706
Max Act: 7.3706. Min Act: -0.1700
Data Index: 7713464 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8706. Min Range: -7.8706
Max Act: 7.3394. Min Act: -0.1700
Data Index: 2056534 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8706. Min Range: -7.8706
Max Act: 7.3394. Min Act: -0.1700
Data Index: 8716265 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8706. Min Range: -7.8706
Max Act: 7.3081. Min Act: -0.1700
Data Index: 3358426 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8706. Min Range: -7.8706
Max Act: 7.2144. Min Act: -0.1700
Data Index: 4615065 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8706. Min Range: -7.8706
Max Act: 7.1831. Min Act: -0.1700
Data Index: 70317 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8706. Min Range: -7.8706
Max Act: 7.2144. Min Act: -0.1700
Data Index: 1101675 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8706. Min Range: -7.8706
Max Act: 7.1519. Min Act: -0.1700
Data Index: 2117535 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8706. Min Range: -7.8706
Max Act: 7.1519. Min Act: -0.1700
Data Index: 2856044 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8706. Min Range: -7.8706
Max Act: 7.0581. Min Act: -0.1700
Data Index: 3827931 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8706. Min Range: -7.8706
Max Act: 7.1206. Min Act: -0.1700
Data Index: 3643770 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8706. Min Range: -7.8706
Max Act: 7.0894. Min Act: -0.1700
Data Index: 4224717 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8706. Min Range: -7.8706
Max Act: 7.0894. Min Act: -0.1700
Data Index: 770728 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8706. Min Range: -7.8706
Max Act: 7.0581. Min Act: -0.1700
Data Index: 4743445 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8706. Min Range: -7.8706
Max Act: 7.0269. Min Act: -0.1700
Data Index: 4329324 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8706. Min Range: -7.8706
Max Act: 7.0269. Min Act: -0.1700
Data Index: 7271665 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #19