Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2586 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2262. Min Range: -5.2262
Max Act: 5.2262. Min Act: -0.1700
Data Index: 41024 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2262. Min Range: -5.2262
Max Act: 5.1325. Min Act: -0.1700
Data Index: 5944316 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2262. Min Range: -5.2262
Max Act: 5.0387. Min Act: -0.1700
Data Index: 5944317 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2262. Min Range: -5.2262
Max Act: 5.0075. Min Act: -0.1700
Data Index: 5852906 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2262. Min Range: -5.2262
Max Act: 4.9762. Min Act: -0.1700
Data Index: 3940657 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2262. Min Range: -5.2262
Max Act: 4.9450. Min Act: -0.1700
Data Index: 1777465 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2262. Min Range: -5.2262
Max Act: 4.9137. Min Act: -0.1700
Data Index: 6597849 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2262. Min Range: -5.2262
Max Act: 4.9137. Min Act: -0.1700
Data Index: 6500012 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2262. Min Range: -5.2262
Max Act: 4.9137. Min Act: -0.1700
Data Index: 485803 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2262. Min Range: -5.2262
Max Act: 4.9137. Min Act: -0.1700
Data Index: 6258035 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2262. Min Range: -5.2262
Max Act: 4.8512. Min Act: -0.1700
Data Index: 3066155 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2262. Min Range: -5.2262
Max Act: 4.8512. Min Act: -0.1700
Data Index: 6212173 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2262. Min Range: -5.2262
Max Act: 4.8512. Min Act: -0.1700
Data Index: 3535210 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2262. Min Range: -5.2262
Max Act: 4.8512. Min Act: -0.1700
Data Index: 4992223 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2262. Min Range: -5.2262
Max Act: 4.8200. Min Act: -0.1700
Data Index: 1001564 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2262. Min Range: -5.2262
Max Act: 4.8200. Min Act: -0.1700
Data Index: 7598251 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2262. Min Range: -5.2262
Max Act: 4.7575. Min Act: -0.1700
Data Index: 1920390 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2262. Min Range: -5.2262
Max Act: 4.7887. Min Act: -0.1700
Data Index: 1658926 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2262. Min Range: -5.2262
Max Act: 4.7887. Min Act: -0.1700
Data Index: 3136449 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2262. Min Range: -5.2262
Max Act: 4.7575. Min Act: -0.1700
Data Index: 6219710 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #19