Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2422 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6294. Min Range: -5.6294
Max Act: 5.6294. Min Act: -0.1700
Data Index: 3199843 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6294. Min Range: -5.6294
Max Act: 5.6294. Min Act: -0.1700
Data Index: 3683971 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6294. Min Range: -5.6294
Max Act: 5.4419. Min Act: -0.1700
Data Index: 4779958 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6294. Min Range: -5.6294
Max Act: 5.3794. Min Act: -0.1700
Data Index: 494342 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6294. Min Range: -5.6294
Max Act: 5.3794. Min Act: -0.1700
Data Index: 5987939 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6294. Min Range: -5.6294
Max Act: 5.3482. Min Act: -0.1700
Data Index: 6331381 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6294. Min Range: -5.6294
Max Act: 5.3482. Min Act: -0.1700
Data Index: 7821262 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6294. Min Range: -5.6294
Max Act: 5.3169. Min Act: -0.1700
Data Index: 2493109 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6294. Min Range: -5.6294
Max Act: 5.3169. Min Act: -0.1700
Data Index: 3810174 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6294. Min Range: -5.6294
Max Act: 5.3169. Min Act: -0.1700
Data Index: 6516166 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6294. Min Range: -5.6294
Max Act: 5.2857. Min Act: -0.1700
Data Index: 3340740 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6294. Min Range: -5.6294
Max Act: 5.3169. Min Act: -0.1700
Data Index: 6196844 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6294. Min Range: -5.6294
Max Act: 5.2544. Min Act: -0.1700
Data Index: 5117387 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6294. Min Range: -5.6294
Max Act: 5.2857. Min Act: -0.1700
Data Index: 4711415 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6294. Min Range: -5.6294
Max Act: 5.2544. Min Act: -0.1700
Data Index: 6391072 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6294. Min Range: -5.6294
Max Act: 5.2232. Min Act: -0.1700
Data Index: 1336093 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6294. Min Range: -5.6294
Max Act: 5.2232. Min Act: -0.1700
Data Index: 32727 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6294. Min Range: -5.6294
Max Act: 5.1919. Min Act: -0.1700
Data Index: 4547172 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6294. Min Range: -5.6294
Max Act: 5.1919. Min Act: -0.1700
Data Index: 764873 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6294. Min Range: -5.6294
Max Act: 5.1607. Min Act: -0.1700
Data Index: 3288597 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #19