Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3518 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9233. Min Range: -7.9233
Max Act: 7.9233. Min Act: -0.1700
Data Index: 8496845 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9233. Min Range: -7.9233
Max Act: 7.3295. Min Act: -0.1700
Data Index: 8096749 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9233. Min Range: -7.9233
Max Act: 7.2358. Min Act: -0.1700
Data Index: 4880294 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9233. Min Range: -7.9233
Max Act: 7.2670. Min Act: -0.1700
Data Index: 3586534 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9233. Min Range: -7.9233
Max Act: 7.2670. Min Act: -0.1700
Data Index: 5711688 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9233. Min Range: -7.9233
Max Act: 7.1733. Min Act: -0.1700
Data Index: 1032539 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9233. Min Range: -7.9233
Max Act: 7.2045. Min Act: -0.1700
Data Index: 8126401 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9233. Min Range: -7.9233
Max Act: 7.2045. Min Act: -0.1700
Data Index: 5820608 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9233. Min Range: -7.9233
Max Act: 7.1733. Min Act: -0.1700
Data Index: 997781 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9233. Min Range: -7.9233
Max Act: 7.1733. Min Act: -0.1700
Data Index: 3436048 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9233. Min Range: -7.9233
Max Act: 7.1733. Min Act: -0.1700
Data Index: 2866296 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9233. Min Range: -7.9233
Max Act: 7.1420. Min Act: -0.1700
Data Index: 8758652 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9233. Min Range: -7.9233
Max Act: 7.1420. Min Act: -0.1700
Data Index: 5627891 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9233. Min Range: -7.9233
Max Act: 7.0795. Min Act: -0.1700
Data Index: 7198905 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9233. Min Range: -7.9233
Max Act: 7.0795. Min Act: -0.1700
Data Index: 3316699 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9233. Min Range: -7.9233
Max Act: 7.0795. Min Act: -0.1700
Data Index: 7168149 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9233. Min Range: -7.9233
Max Act: 7.0795. Min Act: -0.1700
Data Index: 4356038 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9233. Min Range: -7.9233
Max Act: 7.0483. Min Act: -0.1700
Data Index: 6493088 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9233. Min Range: -7.9233
Max Act: 7.0483. Min Act: -0.1700
Data Index: 5386090 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9233. Min Range: -7.9233
Max Act: 7.0483. Min Act: -0.1700
Data Index: 2731157 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #19