Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1360 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.8136. Min Range: -8.8136
Max Act: 8.8136. Min Act: -0.1700
Data Index: 5405297 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.8136. Min Range: -8.8136
Max Act: 8.7511. Min Act: -0.1700
Data Index: 363090 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.8136. Min Range: -8.8136
Max Act: 8.6886. Min Act: -0.1700
Data Index: 6971749 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.8136. Min Range: -8.8136
Max Act: 8.6886. Min Act: -0.1700
Data Index: 6762530 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.8136. Min Range: -8.8136
Max Act: 8.6886. Min Act: -0.1700
Data Index: 206916 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.8136. Min Range: -8.8136
Max Act: 8.6886. Min Act: -0.1700
Data Index: 846735 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.8136. Min Range: -8.8136
Max Act: 8.6886. Min Act: -0.1700
Data Index: 5100259 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.8136. Min Range: -8.8136
Max Act: 8.6886. Min Act: -0.1700
Data Index: 29083 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.8136. Min Range: -8.8136
Max Act: 8.5636. Min Act: -0.1700
Data Index: 2570666 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.8136. Min Range: -8.8136
Max Act: 8.5011. Min Act: -0.1700
Data Index: 5926985 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.8136. Min Range: -8.8136
Max Act: 8.5636. Min Act: -0.1700
Data Index: 2814407 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.8136. Min Range: -8.8136
Max Act: 8.5636. Min Act: -0.1700
Data Index: 4070038 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.8136. Min Range: -8.8136
Max Act: 8.5636. Min Act: -0.1700
Data Index: 5058814 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.8136. Min Range: -8.8136
Max Act: 8.5636. Min Act: -0.1700
Data Index: 8382583 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.8136. Min Range: -8.8136
Max Act: 8.5011. Min Act: -0.1700
Data Index: 8426423 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.8136. Min Range: -8.8136
Max Act: 8.5011. Min Act: -0.1700
Data Index: 5534430 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.8136. Min Range: -8.8136
Max Act: 8.5011. Min Act: -0.1700
Data Index: 2142412 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.8136. Min Range: -8.8136
Max Act: 8.4698. Min Act: -0.1700
Data Index: 7102815 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.8136. Min Range: -8.8136
Max Act: 8.4698. Min Act: -0.1700
Data Index: 3158932 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.8136. Min Range: -8.8136
Max Act: 8.4073. Min Act: -0.1700
Data Index: 2934585 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #19