Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4655 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6352. Min Range: -4.6352
Max Act: 4.6352. Min Act: -0.1700
Data Index: 1656119 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6352. Min Range: -4.6352
Max Act: 4.6352. Min Act: -0.1700
Data Index: 6771328 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6352. Min Range: -4.6352
Max Act: 4.6040. Min Act: -0.1700
Data Index: 4678693 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6352. Min Range: -4.6352
Max Act: 4.6040. Min Act: -0.1700
Data Index: 1822883 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6352. Min Range: -4.6352
Max Act: 4.4477. Min Act: -0.1700
Data Index: 8434953 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6352. Min Range: -4.6352
Max Act: 4.4790. Min Act: -0.1700
Data Index: 4840971 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6352. Min Range: -4.6352
Max Act: 4.4477. Min Act: -0.1700
Data Index: 6113851 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6352. Min Range: -4.6352
Max Act: 4.4477. Min Act: -0.1700
Data Index: 4659189 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6352. Min Range: -4.6352
Max Act: 4.4477. Min Act: -0.1700
Data Index: 5666326 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6352. Min Range: -4.6352
Max Act: 4.4477. Min Act: -0.1700
Data Index: 4413662 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6352. Min Range: -4.6352
Max Act: 4.4477. Min Act: -0.1700
Data Index: 6501925 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6352. Min Range: -4.6352
Max Act: 4.4165. Min Act: -0.1700
Data Index: 780624 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6352. Min Range: -4.6352
Max Act: 4.4165. Min Act: -0.1700
Data Index: 2555902 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6352. Min Range: -4.6352
Max Act: 4.3852. Min Act: -0.1700
Data Index: 8402560 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6352. Min Range: -4.6352
Max Act: 4.3540. Min Act: -0.1700
Data Index: 2698453 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6352. Min Range: -4.6352
Max Act: 4.3540. Min Act: -0.1700
Data Index: 4285408 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6352. Min Range: -4.6352
Max Act: 4.3540. Min Act: -0.1700
Data Index: 4749275 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6352. Min Range: -4.6352
Max Act: 4.3227. Min Act: -0.1700
Data Index: 6502447 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6352. Min Range: -4.6352
Max Act: 4.3540. Min Act: -0.1700
Data Index: 3440094 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6352. Min Range: -4.6352
Max Act: 4.3540. Min Act: -0.1700
Data Index: 1785643 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #19