Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 18 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8692. Min Range: -4.8692
Max Act: 4.8692. Min Act: -0.1700
Data Index: 4690623 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8692. Min Range: -4.8692
Max Act: 4.8067. Min Act: -0.1700
Data Index: 708706 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8692. Min Range: -4.8692
Max Act: 4.7130. Min Act: -0.1700
Data Index: 3016740 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8692. Min Range: -4.8692
Max Act: 4.6817. Min Act: -0.1700
Data Index: 8487919 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8692. Min Range: -4.8692
Max Act: 4.7130. Min Act: -0.1700
Data Index: 3530502 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8692. Min Range: -4.8692
Max Act: 4.6192. Min Act: -0.1700
Data Index: 2464140 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8692. Min Range: -4.8692
Max Act: 4.6192. Min Act: -0.1700
Data Index: 3209800 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8692. Min Range: -4.8692
Max Act: 4.5567. Min Act: -0.1700
Data Index: 3746683 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8692. Min Range: -4.8692
Max Act: 4.5880. Min Act: -0.1700
Data Index: 490878 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8692. Min Range: -4.8692
Max Act: 4.5880. Min Act: -0.1700
Data Index: 603907 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8692. Min Range: -4.8692
Max Act: 4.5567. Min Act: -0.1700
Data Index: 5555047 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8692. Min Range: -4.8692
Max Act: 4.5255. Min Act: -0.1700
Data Index: 3886765 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8692. Min Range: -4.8692
Max Act: 4.5567. Min Act: -0.1700
Data Index: 1233105 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8692. Min Range: -4.8692
Max Act: 4.5255. Min Act: -0.1700
Data Index: 3727293 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8692. Min Range: -4.8692
Max Act: 4.5255. Min Act: -0.1700
Data Index: 2249601 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8692. Min Range: -4.8692
Max Act: 4.5255. Min Act: -0.1700
Data Index: 6334668 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8692. Min Range: -4.8692
Max Act: 4.5255. Min Act: -0.1700
Data Index: 2279932 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8692. Min Range: -4.8692
Max Act: 4.4942. Min Act: -0.1700
Data Index: 5089485 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8692. Min Range: -4.8692
Max Act: 4.4630. Min Act: -0.1700
Data Index: 6275248 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8692. Min Range: -4.8692
Max Act: 4.4942. Min Act: -0.1700
Data Index: 2415827 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #19