Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1904 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.4351. Min Range: -4.4351
Max Act: 4.4351. Min Act: -0.1700
Data Index: 4675838 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4351. Min Range: -4.4351
Max Act: 4.2788. Min Act: -0.1700
Data Index: 1999293 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4351. Min Range: -4.4351
Max Act: 4.3101. Min Act: -0.1700
Data Index: 6666958 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4351. Min Range: -4.4351
Max Act: 4.1850. Min Act: -0.1700
Data Index: 739788 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4351. Min Range: -4.4351
Max Act: 4.1850. Min Act: -0.1700
Data Index: 2441400 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4351. Min Range: -4.4351
Max Act: 4.1225. Min Act: -0.1700
Data Index: 4400764 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4351. Min Range: -4.4351
Max Act: 4.0913. Min Act: -0.1700
Data Index: 8113131 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4351. Min Range: -4.4351
Max Act: 4.1069. Min Act: -0.1700
Data Index: 8323138 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4351. Min Range: -4.4351
Max Act: 4.0444. Min Act: -0.1700
Data Index: 7279678 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4351. Min Range: -4.4351
Max Act: 4.0444. Min Act: -0.1700
Data Index: 3513321 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4351. Min Range: -4.4351
Max Act: 4.0288. Min Act: -0.1700
Data Index: 2028303 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4351. Min Range: -4.4351
Max Act: 4.0288. Min Act: -0.1700
Data Index: 1333970 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4351. Min Range: -4.4351
Max Act: 4.0600. Min Act: -0.1700
Data Index: 2905683 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4351. Min Range: -4.4351
Max Act: 4.0444. Min Act: -0.1700
Data Index: 429396 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4351. Min Range: -4.4351
Max Act: 3.9975. Min Act: -0.1700
Data Index: 2640448 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4351. Min Range: -4.4351
Max Act: 4.0288. Min Act: -0.1700
Data Index: 5042305 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4351. Min Range: -4.4351
Max Act: 3.9819. Min Act: -0.1700
Data Index: 8298060 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4351. Min Range: -4.4351
Max Act: 3.9975. Min Act: -0.1700
Data Index: 6065158 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4351. Min Range: -4.4351
Max Act: 3.9819. Min Act: -0.1700
Data Index: 2014883 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4351. Min Range: -4.4351
Max Act: 3.9662. Min Act: -0.1700
Data Index: 3483724 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #19