Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1954 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8384. Min Range: -5.8384
Max Act: 5.8384. Min Act: -0.1700
Data Index: 2355427 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8384. Min Range: -5.8384
Max Act: 5.4322. Min Act: -0.1700
Data Index: 7182827 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8384. Min Range: -5.8384
Max Act: 5.3072. Min Act: -0.1700
Data Index: 6404288 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8384. Min Range: -5.8384
Max Act: 5.3072. Min Act: -0.1700
Data Index: 6066152 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8384. Min Range: -5.8384
Max Act: 5.2134. Min Act: -0.1700
Data Index: 7497643 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8384. Min Range: -5.8384
Max Act: 5.2134. Min Act: -0.1700
Data Index: 4345780 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8384. Min Range: -5.8384
Max Act: 5.1197. Min Act: -0.1700
Data Index: 5114802 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8384. Min Range: -5.8384
Max Act: 5.1509. Min Act: -0.1700
Data Index: 1915258 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8384. Min Range: -5.8384
Max Act: 5.1509. Min Act: -0.1700
Data Index: 1893913 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8384. Min Range: -5.8384
Max Act: 5.1197. Min Act: -0.1700
Data Index: 5050946 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8384. Min Range: -5.8384
Max Act: 5.0884. Min Act: -0.1700
Data Index: 1985109 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8384. Min Range: -5.8384
Max Act: 5.0884. Min Act: -0.1700
Data Index: 5793739 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8384. Min Range: -5.8384
Max Act: 5.1197. Min Act: -0.1700
Data Index: 3822893 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8384. Min Range: -5.8384
Max Act: 5.0884. Min Act: -0.1700
Data Index: 8614091 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8384. Min Range: -5.8384
Max Act: 5.0884. Min Act: -0.1700
Data Index: 6404285 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8384. Min Range: -5.8384
Max Act: 5.0259. Min Act: -0.1700
Data Index: 4767724 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8384. Min Range: -5.8384
Max Act: 5.0572. Min Act: -0.1700
Data Index: 2312226 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8384. Min Range: -5.8384
Max Act: 5.0572. Min Act: -0.1700
Data Index: 640514 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8384. Min Range: -5.8384
Max Act: 5.0259. Min Act: -0.1700
Data Index: 710858 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8384. Min Range: -5.8384
Max Act: 4.9947. Min Act: -0.1700
Data Index: 2603108 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #19