Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2125 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3363. Min Range: -6.3363
Max Act: 6.3363. Min Act: -0.1700
Data Index: 536145 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3363. Min Range: -6.3363
Max Act: 6.2738. Min Act: -0.1700
Data Index: 657906 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3363. Min Range: -6.3363
Max Act: 6.1801. Min Act: -0.1700
Data Index: 5898183 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3363. Min Range: -6.3363
Max Act: 6.1801. Min Act: -0.1700
Data Index: 7517835 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3363. Min Range: -6.3363
Max Act: 6.1488. Min Act: -0.1700
Data Index: 8556536 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3363. Min Range: -6.3363
Max Act: 6.1176. Min Act: -0.1700
Data Index: 3776742 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3363. Min Range: -6.3363
Max Act: 6.1176. Min Act: -0.1700
Data Index: 3905845 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3363. Min Range: -6.3363
Max Act: 6.0863. Min Act: -0.1700
Data Index: 2177362 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3363. Min Range: -6.3363
Max Act: 6.0863. Min Act: -0.1700
Data Index: 463785 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3363. Min Range: -6.3363
Max Act: 6.0238. Min Act: -0.1700
Data Index: 1094671 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3363. Min Range: -6.3363
Max Act: 6.0238. Min Act: -0.1700
Data Index: 3172498 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3363. Min Range: -6.3363
Max Act: 5.9926. Min Act: -0.1700
Data Index: 4364390 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3363. Min Range: -6.3363
Max Act: 5.9926. Min Act: -0.1700
Data Index: 2251197 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3363. Min Range: -6.3363
Max Act: 5.9613. Min Act: -0.1700
Data Index: 5670108 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3363. Min Range: -6.3363
Max Act: 5.9613. Min Act: -0.1700
Data Index: 2155095 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3363. Min Range: -6.3363
Max Act: 5.9613. Min Act: -0.1700
Data Index: 8406159 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3363. Min Range: -6.3363
Max Act: 5.9613. Min Act: -0.1700
Data Index: 4837939 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3363. Min Range: -6.3363
Max Act: 5.9613. Min Act: -0.1700
Data Index: 7183823 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3363. Min Range: -6.3363
Max Act: 5.9613. Min Act: -0.1700
Data Index: 360231 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3363. Min Range: -6.3363
Max Act: 5.9301. Min Act: -0.1700
Data Index: 3205025 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #19