Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5863 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9261. Min Range: -5.9261
Max Act: 5.9261. Min Act: -0.1700
Data Index: 5923774 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9261. Min Range: -5.9261
Max Act: 5.8636. Min Act: -0.1700
Data Index: 7067997 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9261. Min Range: -5.9261
Max Act: 5.8636. Min Act: -0.1700
Data Index: 442494 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9261. Min Range: -5.9261
Max Act: 5.8324. Min Act: -0.1700
Data Index: 1769658 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9261. Min Range: -5.9261
Max Act: 5.7386. Min Act: -0.1700
Data Index: 2327223 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9261. Min Range: -5.9261
Max Act: 5.7386. Min Act: -0.1700
Data Index: 8787455 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9261. Min Range: -5.9261
Max Act: 5.7074. Min Act: -0.1700
Data Index: 5879041 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9261. Min Range: -5.9261
Max Act: 5.6761. Min Act: -0.1700
Data Index: 1539195 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9261. Min Range: -5.9261
Max Act: 5.6449. Min Act: -0.1700
Data Index: 1659136 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9261. Min Range: -5.9261
Max Act: 5.6136. Min Act: -0.1700
Data Index: 3378415 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9261. Min Range: -5.9261
Max Act: 5.6136. Min Act: -0.1700
Data Index: 5324867 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9261. Min Range: -5.9261
Max Act: 5.6136. Min Act: -0.1700
Data Index: 4832201 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9261. Min Range: -5.9261
Max Act: 5.6136. Min Act: -0.1700
Data Index: 6314476 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9261. Min Range: -5.9261
Max Act: 5.6449. Min Act: -0.1700
Data Index: 4358206 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9261. Min Range: -5.9261
Max Act: 5.6136. Min Act: -0.1700
Data Index: 8694081 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9261. Min Range: -5.9261
Max Act: 5.5824. Min Act: -0.1700
Data Index: 4085609 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9261. Min Range: -5.9261
Max Act: 5.5824. Min Act: -0.1700
Data Index: 156473 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9261. Min Range: -5.9261
Max Act: 5.5511. Min Act: -0.1700
Data Index: 5206981 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9261. Min Range: -5.9261
Max Act: 5.5199. Min Act: -0.1700
Data Index: 7300680 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9261. Min Range: -5.9261
Max Act: 5.5199. Min Act: -0.1700
Data Index: 6873875 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #19