Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2121 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7617. Min Range: -6.7617
Max Act: 6.7617. Min Act: -0.1700
Data Index: 914347 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7617. Min Range: -6.7617
Max Act: 6.6367. Min Act: -0.1700
Data Index: 8497093 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7617. Min Range: -6.7617
Max Act: 6.3867. Min Act: -0.1700
Data Index: 3117845 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7617. Min Range: -6.7617
Max Act: 6.2304. Min Act: -0.1700
Data Index: 5443932 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7617. Min Range: -6.7617
Max Act: 6.1992. Min Act: -0.1700
Data Index: 8235298 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7617. Min Range: -6.7617
Max Act: 6.1992. Min Act: -0.1700
Data Index: 3668508 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7617. Min Range: -6.7617
Max Act: 6.1992. Min Act: -0.1700
Data Index: 6674444 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7617. Min Range: -6.7617
Max Act: 6.1679. Min Act: -0.1700
Data Index: 3528303 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7617. Min Range: -6.7617
Max Act: 6.1679. Min Act: -0.1700
Data Index: 2713691 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7617. Min Range: -6.7617
Max Act: 6.1679. Min Act: -0.1700
Data Index: 6573630 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7617. Min Range: -6.7617
Max Act: 6.1679. Min Act: -0.1700
Data Index: 3914327 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7617. Min Range: -6.7617
Max Act: 6.1679. Min Act: -0.1700
Data Index: 4920412 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7617. Min Range: -6.7617
Max Act: 6.0742. Min Act: -0.1700
Data Index: 7745176 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7617. Min Range: -6.7617
Max Act: 6.0742. Min Act: -0.1700
Data Index: 6647325 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7617. Min Range: -6.7617
Max Act: 6.0429. Min Act: -0.1700
Data Index: 7868356 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7617. Min Range: -6.7617
Max Act: 6.0429. Min Act: -0.1700
Data Index: 3441128 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7617. Min Range: -6.7617
Max Act: 6.0429. Min Act: -0.1700
Data Index: 8501342 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7617. Min Range: -6.7617
Max Act: 6.0117. Min Act: -0.1700
Data Index: 928388 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7617. Min Range: -6.7617
Max Act: 5.9804. Min Act: -0.1700
Data Index: 1225107 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7617. Min Range: -6.7617
Max Act: 5.9804. Min Act: -0.1700
Data Index: 8141060 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #19