Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4597 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.9133. Min Range: -5.9133
Max Act: 5.9133. Min Act: -0.1700
Data Index: 6364984 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9133. Min Range: -5.9133
Max Act: 5.7883. Min Act: -0.1700
Data Index: 6261000 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9133. Min Range: -5.9133
Max Act: 5.7258. Min Act: -0.1700
Data Index: 2020578 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9133. Min Range: -5.9133
Max Act: 5.6946. Min Act: -0.1700
Data Index: 6659161 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9133. Min Range: -5.9133
Max Act: 5.7258. Min Act: -0.1700
Data Index: 8255601 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9133. Min Range: -5.9133
Max Act: 5.6946. Min Act: -0.1700
Data Index: 1727301 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9133. Min Range: -5.9133
Max Act: 5.6633. Min Act: -0.1700
Data Index: 3291973 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9133. Min Range: -5.9133
Max Act: 5.6633. Min Act: -0.1700
Data Index: 4095882 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9133. Min Range: -5.9133
Max Act: 5.6321. Min Act: -0.1700
Data Index: 4904585 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9133. Min Range: -5.9133
Max Act: 5.6321. Min Act: -0.1700
Data Index: 8211945 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9133. Min Range: -5.9133
Max Act: 5.6008. Min Act: -0.1700
Data Index: 1671388 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9133. Min Range: -5.9133
Max Act: 5.6008. Min Act: -0.1700
Data Index: 23651 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9133. Min Range: -5.9133
Max Act: 5.6008. Min Act: -0.1700
Data Index: 6261003 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9133. Min Range: -5.9133
Max Act: 5.6008. Min Act: -0.1700
Data Index: 6580812 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9133. Min Range: -5.9133
Max Act: 5.5696. Min Act: -0.1700
Data Index: 6926334 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9133. Min Range: -5.9133
Max Act: 5.5383. Min Act: -0.1700
Data Index: 2951859 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9133. Min Range: -5.9133
Max Act: 5.5383. Min Act: -0.1700
Data Index: 2143186 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9133. Min Range: -5.9133
Max Act: 5.5071. Min Act: -0.1700
Data Index: 987069 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9133. Min Range: -5.9133
Max Act: 5.5383. Min Act: -0.1700
Data Index: 2336801 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9133. Min Range: -5.9133
Max Act: 5.5383. Min Act: -0.1700
Data Index: 5555863 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #19