Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2576 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9923. Min Range: -7.9923
Max Act: 7.9923. Min Act: -0.1700
Data Index: 574088 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9923. Min Range: -7.9923
Max Act: 7.5548. Min Act: -0.1700
Data Index: 5525991 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9923. Min Range: -7.9923
Max Act: 7.5548. Min Act: -0.1700
Data Index: 1610613 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9923. Min Range: -7.9923
Max Act: 7.5548. Min Act: -0.1700
Data Index: 6776523 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9923. Min Range: -7.9923
Max Act: 7.5235. Min Act: -0.1700
Data Index: 3738919 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9923. Min Range: -7.9923
Max Act: 7.4923. Min Act: -0.1700
Data Index: 7741402 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9923. Min Range: -7.9923
Max Act: 7.4610. Min Act: -0.1700
Data Index: 497518 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9923. Min Range: -7.9923
Max Act: 7.4610. Min Act: -0.1700
Data Index: 8037644 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9923. Min Range: -7.9923
Max Act: 7.4298. Min Act: -0.1700
Data Index: 7476411 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9923. Min Range: -7.9923
Max Act: 7.4298. Min Act: -0.1700
Data Index: 8275055 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9923. Min Range: -7.9923
Max Act: 7.4298. Min Act: -0.1700
Data Index: 5248338 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9923. Min Range: -7.9923
Max Act: 7.3985. Min Act: -0.1700
Data Index: 675441 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9923. Min Range: -7.9923
Max Act: 7.3985. Min Act: -0.1700
Data Index: 5302365 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9923. Min Range: -7.9923
Max Act: 7.3985. Min Act: -0.1700
Data Index: 4206274 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9923. Min Range: -7.9923
Max Act: 7.3985. Min Act: -0.1700
Data Index: 1298950 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9923. Min Range: -7.9923
Max Act: 7.3985. Min Act: -0.1700
Data Index: 638157 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9923. Min Range: -7.9923
Max Act: 7.3985. Min Act: -0.1700
Data Index: 6507208 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9923. Min Range: -7.9923
Max Act: 7.3360. Min Act: -0.1700
Data Index: 356816 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9923. Min Range: -7.9923
Max Act: 7.3360. Min Act: -0.1700
Data Index: 3038985 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9923. Min Range: -7.9923
Max Act: 7.3360. Min Act: -0.1700
Data Index: 1954163 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #19