Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2628 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.7985. Min Range: -5.7985
Max Act: 5.7673. Min Act: -0.1700
Data Index: 7165157 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7985. Min Range: -5.7985
Max Act: 5.7985. Min Act: -0.1700
Data Index: 5559160 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7985. Min Range: -5.7985
Max Act: 5.7673. Min Act: -0.1700
Data Index: 8180944 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7985. Min Range: -5.7985
Max Act: 5.5798. Min Act: -0.1700
Data Index: 73634 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7985. Min Range: -5.7985
Max Act: 5.5485. Min Act: -0.1700
Data Index: 7791574 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7985. Min Range: -5.7985
Max Act: 5.4860. Min Act: -0.1700
Data Index: 424103 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7985. Min Range: -5.7985
Max Act: 5.4548. Min Act: -0.1700
Data Index: 3112116 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7985. Min Range: -5.7985
Max Act: 5.3923. Min Act: -0.1700
Data Index: 2159269 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7985. Min Range: -5.7985
Max Act: 5.3923. Min Act: -0.1700
Data Index: 4423352 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7985. Min Range: -5.7985
Max Act: 5.3610. Min Act: -0.1700
Data Index: 5059693 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7985. Min Range: -5.7985
Max Act: 5.3298. Min Act: -0.1700
Data Index: 7353314 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7985. Min Range: -5.7985
Max Act: 5.3298. Min Act: -0.1700
Data Index: 931874 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7985. Min Range: -5.7985
Max Act: 5.3298. Min Act: -0.1700
Data Index: 4210811 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7985. Min Range: -5.7985
Max Act: 5.2985. Min Act: -0.1700
Data Index: 1977296 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7985. Min Range: -5.7985
Max Act: 5.2985. Min Act: -0.1700
Data Index: 1294101 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7985. Min Range: -5.7985
Max Act: 5.2985. Min Act: -0.1700
Data Index: 3901214 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7985. Min Range: -5.7985
Max Act: 5.2673. Min Act: -0.1700
Data Index: 7270404 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7985. Min Range: -5.7985
Max Act: 5.2985. Min Act: -0.1700
Data Index: 685879 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7985. Min Range: -5.7985
Max Act: 5.2673. Min Act: -0.1700
Data Index: 5242250 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7985. Min Range: -5.7985
Max Act: 5.2360. Min Act: -0.1700
Data Index: 384095 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #19