Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4326 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.9187. Min Range: -3.9187
Max Act: 3.9187. Min Act: -0.1700
Data Index: 2830100 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9187. Min Range: -3.9187
Max Act: 3.7311. Min Act: -0.1700
Data Index: 4084193 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9187. Min Range: -3.9187
Max Act: 3.6685. Min Act: -0.1700
Data Index: 3542384 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9187. Min Range: -3.9187
Max Act: 3.6372. Min Act: -0.1700
Data Index: 4615665 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9187. Min Range: -3.9187
Max Act: 3.6372. Min Act: -0.1700
Data Index: 3311430 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9187. Min Range: -3.9187
Max Act: 3.6059. Min Act: -0.1700
Data Index: 5481258 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9187. Min Range: -3.9187
Max Act: 3.6059. Min Act: -0.1700
Data Index: 5212955 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9187. Min Range: -3.9187
Max Act: 3.5746. Min Act: -0.1700
Data Index: 7649599 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9187. Min Range: -3.9187
Max Act: 3.5590. Min Act: -0.1700
Data Index: 7890147 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9187. Min Range: -3.9187
Max Act: 3.5746. Min Act: -0.1700
Data Index: 1978084 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9187. Min Range: -3.9187
Max Act: 3.5590. Min Act: -0.1700
Data Index: 851801 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9187. Min Range: -3.9187
Max Act: 3.5590. Min Act: -0.1700
Data Index: 8673564 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9187. Min Range: -3.9187
Max Act: 3.5590. Min Act: -0.1700
Data Index: 7709291 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9187. Min Range: -3.9187
Max Act: 3.5433. Min Act: -0.1700
Data Index: 3838581 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9187. Min Range: -3.9187
Max Act: 3.5590. Min Act: -0.1700
Data Index: 465152 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9187. Min Range: -3.9187
Max Act: 3.5746. Min Act: -0.1700
Data Index: 1763556 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9187. Min Range: -3.9187
Max Act: 3.5433. Min Act: -0.1700
Data Index: 6026801 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9187. Min Range: -3.9187
Max Act: 3.5433. Min Act: -0.1700
Data Index: 4648244 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9187. Min Range: -3.9187
Max Act: 3.5433. Min Act: -0.1700
Data Index: 4433019 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9187. Min Range: -3.9187
Max Act: 3.5120. Min Act: -0.1700
Data Index: 7845850 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #19