Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2614 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.6849. Min Range: -9.6849
Max Act: 9.6849. Min Act: -0.1700
Data Index: 279131 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.6849. Min Range: -9.6849
Max Act: 9.4349. Min Act: -0.1700
Data Index: 5312383 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.6849. Min Range: -9.6849
Max Act: 9.4349. Min Act: -0.1700
Data Index: 6942219 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.6849. Min Range: -9.6849
Max Act: 9.3724. Min Act: -0.1700
Data Index: 8499743 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.6849. Min Range: -9.6849
Max Act: 9.3724. Min Act: -0.1700
Data Index: 1538482 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.6849. Min Range: -9.6849
Max Act: 9.3724. Min Act: -0.1700
Data Index: 7758615 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.6849. Min Range: -9.6849
Max Act: 9.3724. Min Act: -0.1700
Data Index: 7116493 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.6849. Min Range: -9.6849
Max Act: 9.3099. Min Act: -0.1700
Data Index: 7758614 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.6849. Min Range: -9.6849
Max Act: 9.3099. Min Act: -0.1700
Data Index: 3356793 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.6849. Min Range: -9.6849
Max Act: 9.3099. Min Act: -0.1700
Data Index: 1029305 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.6849. Min Range: -9.6849
Max Act: 9.2474. Min Act: -0.1700
Data Index: 5613559 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.6849. Min Range: -9.6849
Max Act: 9.2474. Min Act: -0.1700
Data Index: 7910499 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.6849. Min Range: -9.6849
Max Act: 9.2474. Min Act: -0.1700
Data Index: 6419783 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.6849. Min Range: -9.6849
Max Act: 9.1849. Min Act: -0.1700
Data Index: 2394652 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.6849. Min Range: -9.6849
Max Act: 9.1849. Min Act: -0.1700
Data Index: 5551658 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.6849. Min Range: -9.6849
Max Act: 9.1849. Min Act: -0.1700
Data Index: 549372 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.6849. Min Range: -9.6849
Max Act: 9.1224. Min Act: -0.1700
Data Index: 3970791 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.6849. Min Range: -9.6849
Max Act: 9.1224. Min Act: -0.1700
Data Index: 3538779 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.6849. Min Range: -9.6849
Max Act: 9.1224. Min Act: -0.1700
Data Index: 2182116 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.6849. Min Range: -9.6849
Max Act: 9.1224. Min Act: -0.1700
Data Index: 2040882 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #19