Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5702 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9677. Min Range: -3.9677
Max Act: 3.9677. Min Act: -0.1700
Data Index: 6910076 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9677. Min Range: -3.9677
Max Act: 3.9052. Min Act: -0.1700
Data Index: 1246828 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9677. Min Range: -3.9677
Max Act: 3.7801. Min Act: -0.1700
Data Index: 4104635 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9677. Min Range: -3.9677
Max Act: 3.7488. Min Act: -0.1700
Data Index: 1981793 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9677. Min Range: -3.9677
Max Act: 3.7488. Min Act: -0.1700
Data Index: 684154 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9677. Min Range: -3.9677
Max Act: 3.7175. Min Act: -0.1700
Data Index: 5325920 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9677. Min Range: -3.9677
Max Act: 3.7175. Min Act: -0.1700
Data Index: 3221222 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9677. Min Range: -3.9677
Max Act: 3.7019. Min Act: -0.1700
Data Index: 7304221 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9677. Min Range: -3.9677
Max Act: 3.6706. Min Act: -0.1700
Data Index: 133088 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9677. Min Range: -3.9677
Max Act: 3.6706. Min Act: -0.1700
Data Index: 4039731 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9677. Min Range: -3.9677
Max Act: 3.6706. Min Act: -0.1700
Data Index: 8226441 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9677. Min Range: -3.9677
Max Act: 3.6862. Min Act: -0.1700
Data Index: 1213985 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9677. Min Range: -3.9677
Max Act: 3.6706. Min Act: -0.1700
Data Index: 696251 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9677. Min Range: -3.9677
Max Act: 3.6549. Min Act: -0.1700
Data Index: 1227351 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9677. Min Range: -3.9677
Max Act: 3.6393. Min Act: -0.1700
Data Index: 7415238 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9677. Min Range: -3.9677
Max Act: 3.6393. Min Act: -0.1700
Data Index: 2473716 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9677. Min Range: -3.9677
Max Act: 3.6393. Min Act: -0.1700
Data Index: 460153 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9677. Min Range: -3.9677
Max Act: 3.6393. Min Act: -0.1700
Data Index: 7182751 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9677. Min Range: -3.9677
Max Act: 3.6393. Min Act: -0.1700
Data Index: 4627137 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9677. Min Range: -3.9677
Max Act: 3.6236. Min Act: -0.1700
Data Index: 1870010 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #19