Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3390 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.8502. Min Range: -7.8502
Max Act: 7.8502. Min Act: -0.1700
Data Index: 7604848 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8502. Min Range: -7.8502
Max Act: 7.7252. Min Act: -0.1700
Data Index: 1871981 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8502. Min Range: -7.8502
Max Act: 7.5377. Min Act: -0.1700
Data Index: 3408709 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8502. Min Range: -7.8502
Max Act: 7.6002. Min Act: -0.1700
Data Index: 7949529 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8502. Min Range: -7.8502
Max Act: 7.4752. Min Act: -0.1700
Data Index: 5141321 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8502. Min Range: -7.8502
Max Act: 7.5377. Min Act: -0.1700
Data Index: 2430225 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8502. Min Range: -7.8502
Max Act: 7.4752. Min Act: -0.1700
Data Index: 2509521 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8502. Min Range: -7.8502
Max Act: 7.4752. Min Act: -0.1700
Data Index: 2092760 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8502. Min Range: -7.8502
Max Act: 7.4752. Min Act: -0.1700
Data Index: 997585 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8502. Min Range: -7.8502
Max Act: 7.3815. Min Act: -0.1700
Data Index: 4300550 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8502. Min Range: -7.8502
Max Act: 7.3502. Min Act: -0.1700
Data Index: 8339075 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8502. Min Range: -7.8502
Max Act: 7.3815. Min Act: -0.1700
Data Index: 432623 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8502. Min Range: -7.8502
Max Act: 7.3190. Min Act: -0.1700
Data Index: 4157236 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8502. Min Range: -7.8502
Max Act: 7.3190. Min Act: -0.1700
Data Index: 1314392 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8502. Min Range: -7.8502
Max Act: 7.3502. Min Act: -0.1700
Data Index: 2837627 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8502. Min Range: -7.8502
Max Act: 7.2877. Min Act: -0.1700
Data Index: 7250468 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8502. Min Range: -7.8502
Max Act: 7.3190. Min Act: -0.1700
Data Index: 6076997 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8502. Min Range: -7.8502
Max Act: 7.3190. Min Act: -0.1700
Data Index: 6959169 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8502. Min Range: -7.8502
Max Act: 7.2877. Min Act: -0.1700
Data Index: 2598070 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8502. Min Range: -7.8502
Max Act: 7.3190. Min Act: -0.1700
Data Index: 2655114 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #19