Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4776 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9937. Min Range: -4.9937
Max Act: 4.9937. Min Act: -0.1700
Data Index: 2140997 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9937. Min Range: -4.9937
Max Act: 4.9000. Min Act: -0.1700
Data Index: 3593454 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9937. Min Range: -4.9937
Max Act: 4.8375. Min Act: -0.1700
Data Index: 2262120 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9937. Min Range: -4.9937
Max Act: 4.8375. Min Act: -0.1700
Data Index: 1494985 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9937. Min Range: -4.9937
Max Act: 4.8375. Min Act: -0.1700
Data Index: 1152297 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9937. Min Range: -4.9937
Max Act: 4.8062. Min Act: -0.1700
Data Index: 1871340 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9937. Min Range: -4.9937
Max Act: 4.8062. Min Act: -0.1700
Data Index: 3586516 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9937. Min Range: -4.9937
Max Act: 4.8062. Min Act: -0.1700
Data Index: 7521634 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9937. Min Range: -4.9937
Max Act: 4.7750. Min Act: -0.1700
Data Index: 2909901 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9937. Min Range: -4.9937
Max Act: 4.7750. Min Act: -0.1700
Data Index: 2918569 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9937. Min Range: -4.9937
Max Act: 4.7437. Min Act: -0.1700
Data Index: 6159250 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9937. Min Range: -4.9937
Max Act: 4.7125. Min Act: -0.1700
Data Index: 2587541 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9937. Min Range: -4.9937
Max Act: 4.7437. Min Act: -0.1700
Data Index: 5539921 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9937. Min Range: -4.9937
Max Act: 4.7437. Min Act: -0.1700
Data Index: 4181423 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9937. Min Range: -4.9937
Max Act: 4.7125. Min Act: -0.1700
Data Index: 1992225 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9937. Min Range: -4.9937
Max Act: 4.7125. Min Act: -0.1700
Data Index: 6120216 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9937. Min Range: -4.9937
Max Act: 4.6812. Min Act: -0.1700
Data Index: 731660 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9937. Min Range: -4.9937
Max Act: 4.7125. Min Act: -0.1700
Data Index: 1713410 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9937. Min Range: -4.9937
Max Act: 4.7125. Min Act: -0.1700
Data Index: 2360948 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9937. Min Range: -4.9937
Max Act: 4.7125. Min Act: -0.1700
Data Index: 2367387 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #19