Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4974 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4766. Min Range: -4.4766
Max Act: 4.4766. Min Act: -0.1700
Data Index: 3698983 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4766. Min Range: -4.4766
Max Act: 4.3516. Min Act: -0.1700
Data Index: 589141 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4766. Min Range: -4.4766
Max Act: 4.3204. Min Act: -0.1700
Data Index: 2677653 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4766. Min Range: -4.4766
Max Act: 4.3204. Min Act: -0.1700
Data Index: 1597941 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4766. Min Range: -4.4766
Max Act: 4.3204. Min Act: -0.1700
Data Index: 1112775 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4766. Min Range: -4.4766
Max Act: 4.2579. Min Act: -0.1700
Data Index: 8614862 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4766. Min Range: -4.4766
Max Act: 4.2266. Min Act: -0.1700
Data Index: 1336122 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4766. Min Range: -4.4766
Max Act: 4.2579. Min Act: -0.1700
Data Index: 6276180 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4766. Min Range: -4.4766
Max Act: 4.2579. Min Act: -0.1700
Data Index: 1788273 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4766. Min Range: -4.4766
Max Act: 4.2266. Min Act: -0.1700
Data Index: 5903999 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4766. Min Range: -4.4766
Max Act: 4.2266. Min Act: -0.1700
Data Index: 5238651 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4766. Min Range: -4.4766
Max Act: 4.2266. Min Act: -0.1700
Data Index: 2105200 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4766. Min Range: -4.4766
Max Act: 4.2266. Min Act: -0.1700
Data Index: 7913604 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4766. Min Range: -4.4766
Max Act: 4.1954. Min Act: -0.1700
Data Index: 4058229 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4766. Min Range: -4.4766
Max Act: 4.1641. Min Act: -0.1700
Data Index: 5507681 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4766. Min Range: -4.4766
Max Act: 4.1954. Min Act: -0.1700
Data Index: 2359006 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4766. Min Range: -4.4766
Max Act: 4.1954. Min Act: -0.1700
Data Index: 5971196 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4766. Min Range: -4.4766
Max Act: 4.1641. Min Act: -0.1700
Data Index: 6005254 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4766. Min Range: -4.4766
Max Act: 4.1954. Min Act: -0.1700
Data Index: 4681281 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4766. Min Range: -4.4766
Max Act: 4.1954. Min Act: -0.1700
Data Index: 5155349 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #19