Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2155 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.5881. Min Range: -8.5881
Max Act: 8.5881. Min Act: -0.1700
Data Index: 5048675 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5881. Min Range: -8.5881
Max Act: 8.4631. Min Act: -0.1700
Data Index: 3146720 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5881. Min Range: -8.5881
Max Act: 8.2756. Min Act: -0.1700
Data Index: 3555430 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5881. Min Range: -8.5881
Max Act: 8.2131. Min Act: -0.1700
Data Index: 5862012 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5881. Min Range: -8.5881
Max Act: 8.1506. Min Act: -0.1700
Data Index: 8022984 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5881. Min Range: -8.5881
Max Act: 7.9006. Min Act: -0.1700
Data Index: 4010814 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5881. Min Range: -8.5881
Max Act: 7.8381. Min Act: -0.1700
Data Index: 38222 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5881. Min Range: -8.5881
Max Act: 7.7756. Min Act: -0.1700
Data Index: 5120488 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5881. Min Range: -8.5881
Max Act: 7.7756. Min Act: -0.1700
Data Index: 8351987 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5881. Min Range: -8.5881
Max Act: 7.8069. Min Act: -0.1700
Data Index: 3628212 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5881. Min Range: -8.5881
Max Act: 7.7444. Min Act: -0.1700
Data Index: 1584667 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5881. Min Range: -8.5881
Max Act: 7.7131. Min Act: -0.1700
Data Index: 288072 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5881. Min Range: -8.5881
Max Act: 7.7131. Min Act: -0.1700
Data Index: 4781183 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5881. Min Range: -8.5881
Max Act: 7.7131. Min Act: -0.1700
Data Index: 7844524 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5881. Min Range: -8.5881
Max Act: 7.6819. Min Act: -0.1700
Data Index: 7186571 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5881. Min Range: -8.5881
Max Act: 7.6819. Min Act: -0.1700
Data Index: 2700490 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5881. Min Range: -8.5881
Max Act: 7.6819. Min Act: -0.1700
Data Index: 6146602 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5881. Min Range: -8.5881
Max Act: 7.6819. Min Act: -0.1700
Data Index: 4063309 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5881. Min Range: -8.5881
Max Act: 7.6506. Min Act: -0.1700
Data Index: 4567522 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5881. Min Range: -8.5881
Max Act: 7.6194. Min Act: -0.1700
Data Index: 3662814 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #19