Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4167 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6376. Min Range: -4.6376
Max Act: 4.6376. Min Act: -0.1700
Data Index: 4498010 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6376. Min Range: -4.6376
Max Act: 4.5126. Min Act: -0.1700
Data Index: 8261780 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6376. Min Range: -4.6376
Max Act: 4.5126. Min Act: -0.1700
Data Index: 3453169 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6376. Min Range: -4.6376
Max Act: 4.4501. Min Act: -0.1700
Data Index: 4401483 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6376. Min Range: -4.6376
Max Act: 4.3876. Min Act: -0.1700
Data Index: 8539710 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6376. Min Range: -4.6376
Max Act: 4.3564. Min Act: -0.1700
Data Index: 248980 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6376. Min Range: -4.6376
Max Act: 4.3251. Min Act: -0.1700
Data Index: 999990 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6376. Min Range: -4.6376
Max Act: 4.2626. Min Act: -0.1700
Data Index: 1970231 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6376. Min Range: -4.6376
Max Act: 4.2313. Min Act: -0.1700
Data Index: 3607607 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6376. Min Range: -4.6376
Max Act: 4.2001. Min Act: -0.1700
Data Index: 4782895 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6376. Min Range: -4.6376
Max Act: 4.2001. Min Act: -0.1700
Data Index: 6322520 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6376. Min Range: -4.6376
Max Act: 4.2001. Min Act: -0.1700
Data Index: 6384081 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6376. Min Range: -4.6376
Max Act: 4.2001. Min Act: -0.1700
Data Index: 6741133 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6376. Min Range: -4.6376
Max Act: 4.2001. Min Act: -0.1700
Data Index: 8514186 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6376. Min Range: -4.6376
Max Act: 4.2001. Min Act: -0.1700
Data Index: 278499 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6376. Min Range: -4.6376
Max Act: 4.1688. Min Act: -0.1700
Data Index: 8514188 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6376. Min Range: -4.6376
Max Act: 4.1688. Min Act: -0.1700
Data Index: 4216243 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6376. Min Range: -4.6376
Max Act: 4.1688. Min Act: -0.1700
Data Index: 8514221 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6376. Min Range: -4.6376
Max Act: 4.1688. Min Act: -0.1700
Data Index: 2532792 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6376. Min Range: -4.6376
Max Act: 4.1376. Min Act: -0.1700
Data Index: 4142261 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #19