Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3512 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.5638. Min Range: -3.5638
Max Act: 3.5638. Min Act: -0.1700
Data Index: 8759900 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5638. Min Range: -3.5638
Max Act: 3.5325. Min Act: -0.1700
Data Index: 2444056 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5638. Min Range: -3.5638
Max Act: 3.5325. Min Act: -0.1700
Data Index: 1309256 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5638. Min Range: -3.5638
Max Act: 3.5168. Min Act: -0.1700
Data Index: 2983387 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5638. Min Range: -3.5638
Max Act: 3.5012. Min Act: -0.1700
Data Index: 2743465 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5638. Min Range: -3.5638
Max Act: 3.4855. Min Act: -0.1700
Data Index: 7959127 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5638. Min Range: -3.5638
Max Act: 3.4699. Min Act: -0.1700
Data Index: 38113 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5638. Min Range: -3.5638
Max Act: 3.4542. Min Act: -0.1700
Data Index: 579136 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5638. Min Range: -3.5638
Max Act: 3.4542. Min Act: -0.1700
Data Index: 7558223 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5638. Min Range: -3.5638
Max Act: 3.4542. Min Act: -0.1700
Data Index: 3251712 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5638. Min Range: -3.5638
Max Act: 3.4542. Min Act: -0.1700
Data Index: 3668873 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5638. Min Range: -3.5638
Max Act: 3.3915. Min Act: -0.1700
Data Index: 8526069 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5638. Min Range: -3.5638
Max Act: 3.3915. Min Act: -0.1700
Data Index: 4154153 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5638. Min Range: -3.5638
Max Act: 3.3758. Min Act: -0.1700
Data Index: 4091345 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5638. Min Range: -3.5638
Max Act: 3.3758. Min Act: -0.1700
Data Index: 2072643 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5638. Min Range: -3.5638
Max Act: 3.3601. Min Act: -0.1700
Data Index: 2518645 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5638. Min Range: -3.5638
Max Act: 3.3758. Min Act: -0.1700
Data Index: 3919166 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5638. Min Range: -3.5638
Max Act: 3.3444. Min Act: -0.1700
Data Index: 5560874 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5638. Min Range: -3.5638
Max Act: 3.3601. Min Act: -0.1700
Data Index: 8417464 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5638. Min Range: -3.5638
Max Act: 3.3287. Min Act: -0.1700
Data Index: 4865749 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #19