Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3461 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4229. Min Range: -8.4229
Max Act: 8.4229. Min Act: -0.1700
Data Index: 7920144 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4229. Min Range: -8.4229
Max Act: 8.3604. Min Act: -0.1700
Data Index: 6519478 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4229. Min Range: -8.4229
Max Act: 8.2979. Min Act: -0.1700
Data Index: 5051325 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4229. Min Range: -8.4229
Max Act: 8.2354. Min Act: -0.1700
Data Index: 2444698 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4229. Min Range: -8.4229
Max Act: 8.1729. Min Act: -0.1700
Data Index: 2064543 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4229. Min Range: -8.4229
Max Act: 8.1729. Min Act: -0.1700
Data Index: 1080671 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4229. Min Range: -8.4229
Max Act: 8.1729. Min Act: -0.1700
Data Index: 596741 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4229. Min Range: -8.4229
Max Act: 7.9854. Min Act: -0.1700
Data Index: 4849462 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4229. Min Range: -8.4229
Max Act: 7.9229. Min Act: -0.1700
Data Index: 5012880 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4229. Min Range: -8.4229
Max Act: 7.8604. Min Act: -0.1700
Data Index: 1303264 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4229. Min Range: -8.4229
Max Act: 7.9229. Min Act: -0.1700
Data Index: 2311740 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4229. Min Range: -8.4229
Max Act: 7.8604. Min Act: -0.1700
Data Index: 2699366 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4229. Min Range: -8.4229
Max Act: 7.8604. Min Act: -0.1700
Data Index: 8057261 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4229. Min Range: -8.4229
Max Act: 7.7979. Min Act: -0.1700
Data Index: 4138543 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4229. Min Range: -8.4229
Max Act: 7.7354. Min Act: -0.1700
Data Index: 2714430 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4229. Min Range: -8.4229
Max Act: 7.7354. Min Act: -0.1700
Data Index: 4655679 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4229. Min Range: -8.4229
Max Act: 7.7354. Min Act: -0.1700
Data Index: 2571965 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4229. Min Range: -8.4229
Max Act: 7.7354. Min Act: -0.1700
Data Index: 5310201 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4229. Min Range: -8.4229
Max Act: 7.7354. Min Act: -0.1700
Data Index: 5426758 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4229. Min Range: -8.4229
Max Act: 7.6729. Min Act: -0.1700
Data Index: 1790514 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #19