Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2775 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.9383. Min Range: -9.9383
Max Act: 9.9383. Min Act: -0.1700
Data Index: 5507353 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.9383. Min Range: -9.9383
Max Act: 8.8133. Min Act: -0.1700
Data Index: 7376592 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.9383. Min Range: -9.9383
Max Act: 8.8133. Min Act: -0.1700
Data Index: 1972848 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.9383. Min Range: -9.9383
Max Act: 8.6883. Min Act: -0.1700
Data Index: 8534039 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.9383. Min Range: -9.9383
Max Act: 8.6258. Min Act: -0.1700
Data Index: 4400025 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.9383. Min Range: -9.9383
Max Act: 8.5633. Min Act: -0.1700
Data Index: 708630 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.9383. Min Range: -9.9383
Max Act: 8.5633. Min Act: -0.1700
Data Index: 3273819 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.9383. Min Range: -9.9383
Max Act: 8.5008. Min Act: -0.1700
Data Index: 7112578 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.9383. Min Range: -9.9383
Max Act: 8.5008. Min Act: -0.1700
Data Index: 6637154 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.9383. Min Range: -9.9383
Max Act: 8.5008. Min Act: -0.1700
Data Index: 524254 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.9383. Min Range: -9.9383
Max Act: 8.3758. Min Act: -0.1700
Data Index: 3372634 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.9383. Min Range: -9.9383
Max Act: 8.3758. Min Act: -0.1700
Data Index: 7548528 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.9383. Min Range: -9.9383
Max Act: 8.3133. Min Act: -0.1700
Data Index: 1708970 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.9383. Min Range: -9.9383
Max Act: 8.3133. Min Act: -0.1700
Data Index: 1950403 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.9383. Min Range: -9.9383
Max Act: 8.3758. Min Act: -0.1700
Data Index: 3192994 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.9383. Min Range: -9.9383
Max Act: 8.2508. Min Act: -0.1700
Data Index: 273640 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.9383. Min Range: -9.9383
Max Act: 8.2508. Min Act: -0.1700
Data Index: 3093627 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.9383. Min Range: -9.9383
Max Act: 8.2508. Min Act: -0.1700
Data Index: 7310512 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.9383. Min Range: -9.9383
Max Act: 8.2508. Min Act: -0.1700
Data Index: 3551421 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.9383. Min Range: -9.9383
Max Act: 8.2508. Min Act: -0.1700
Data Index: 461730 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #19