Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2734 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.2926. Min Range: -4.2926
Max Act: 4.2926. Min Act: -0.1700
Data Index: 590203 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2926. Min Range: -4.2926
Max Act: 4.2301. Min Act: -0.1700
Data Index: 5810223 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2926. Min Range: -4.2926
Max Act: 4.2301. Min Act: -0.1700
Data Index: 2991543 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2926. Min Range: -4.2926
Max Act: 4.1988. Min Act: -0.1700
Data Index: 7778682 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2926. Min Range: -4.2926
Max Act: 4.1988. Min Act: -0.1700
Data Index: 8138986 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2926. Min Range: -4.2926
Max Act: 4.1988. Min Act: -0.1700
Data Index: 1949325 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2926. Min Range: -4.2926
Max Act: 4.1988. Min Act: -0.1700
Data Index: 4404988 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2926. Min Range: -4.2926
Max Act: 4.1988. Min Act: -0.1700
Data Index: 1337228 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2926. Min Range: -4.2926
Max Act: 4.1988. Min Act: -0.1700
Data Index: 2659458 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2926. Min Range: -4.2926
Max Act: 4.1676. Min Act: -0.1700
Data Index: 7740749 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2926. Min Range: -4.2926
Max Act: 4.1676. Min Act: -0.1700
Data Index: 3990959 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2926. Min Range: -4.2926
Max Act: 4.1676. Min Act: -0.1700
Data Index: 5665556 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2926. Min Range: -4.2926
Max Act: 4.1676. Min Act: -0.1700
Data Index: 8237660 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2926. Min Range: -4.2926
Max Act: 4.1676. Min Act: -0.1700
Data Index: 4350274 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2926. Min Range: -4.2926
Max Act: 4.1363. Min Act: -0.1700
Data Index: 3507931 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2926. Min Range: -4.2926
Max Act: 4.1363. Min Act: -0.1700
Data Index: 306568 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2926. Min Range: -4.2926
Max Act: 4.1676. Min Act: -0.1700
Data Index: 1808357 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2926. Min Range: -4.2926
Max Act: 4.1363. Min Act: -0.1700
Data Index: 3326004 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2926. Min Range: -4.2926
Max Act: 4.1050. Min Act: -0.1700
Data Index: 1095055 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2926. Min Range: -4.2926
Max Act: 4.1363. Min Act: -0.1700
Data Index: 3583206 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #19