Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4090 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.1360. Min Range: -5.1360
Max Act: 5.1360. Min Act: -0.1700
Data Index: 7944663 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1360. Min Range: -5.1360
Max Act: 5.0735. Min Act: -0.1700
Data Index: 8182792 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1360. Min Range: -5.1360
Max Act: 4.9485. Min Act: -0.1700
Data Index: 8362713 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1360. Min Range: -5.1360
Max Act: 4.9173. Min Act: -0.1700
Data Index: 7830664 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1360. Min Range: -5.1360
Max Act: 4.9173. Min Act: -0.1700
Data Index: 4569806 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1360. Min Range: -5.1360
Max Act: 4.8860. Min Act: -0.1700
Data Index: 3348467 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1360. Min Range: -5.1360
Max Act: 4.9173. Min Act: -0.1700
Data Index: 7487402 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1360. Min Range: -5.1360
Max Act: 4.9173. Min Act: -0.1700
Data Index: 5354763 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1360. Min Range: -5.1360
Max Act: 4.8860. Min Act: -0.1700
Data Index: 1760666 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1360. Min Range: -5.1360
Max Act: 4.8860. Min Act: -0.1700
Data Index: 4165381 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1360. Min Range: -5.1360
Max Act: 4.8548. Min Act: -0.1700
Data Index: 8343327 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1360. Min Range: -5.1360
Max Act: 4.8860. Min Act: -0.1700
Data Index: 7062444 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1360. Min Range: -5.1360
Max Act: 4.8235. Min Act: -0.1700
Data Index: 8795989 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1360. Min Range: -5.1360
Max Act: 4.8235. Min Act: -0.1700
Data Index: 5003597 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1360. Min Range: -5.1360
Max Act: 4.8548. Min Act: -0.1700
Data Index: 277435 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1360. Min Range: -5.1360
Max Act: 4.8235. Min Act: -0.1700
Data Index: 8569904 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1360. Min Range: -5.1360
Max Act: 4.8235. Min Act: -0.1700
Data Index: 7318039 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1360. Min Range: -5.1360
Max Act: 4.8235. Min Act: -0.1700
Data Index: 880000 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1360. Min Range: -5.1360
Max Act: 4.8235. Min Act: -0.1700
Data Index: 5457305 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1360. Min Range: -5.1360
Max Act: 4.8235. Min Act: -0.1700
Data Index: 4537788 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #19