Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2299 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0604. Min Range: -7.0604
Max Act: 7.0604. Min Act: -0.1700
Data Index: 5708608 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0604. Min Range: -7.0604
Max Act: 6.9979. Min Act: -0.1700
Data Index: 4037373 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0604. Min Range: -7.0604
Max Act: 6.9979. Min Act: -0.1700
Data Index: 6068847 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0604. Min Range: -7.0604
Max Act: 6.9666. Min Act: -0.1700
Data Index: 2624743 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0604. Min Range: -7.0604
Max Act: 6.9041. Min Act: -0.1700
Data Index: 5749565 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0604. Min Range: -7.0604
Max Act: 6.9354. Min Act: -0.1700
Data Index: 3130093 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0604. Min Range: -7.0604
Max Act: 6.8729. Min Act: -0.1700
Data Index: 561432 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0604. Min Range: -7.0604
Max Act: 6.8729. Min Act: -0.1700
Data Index: 1459218 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0604. Min Range: -7.0604
Max Act: 6.8416. Min Act: -0.1700
Data Index: 1000552 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0604. Min Range: -7.0604
Max Act: 6.8104. Min Act: -0.1700
Data Index: 1882069 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0604. Min Range: -7.0604
Max Act: 6.8104. Min Act: -0.1700
Data Index: 451315 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0604. Min Range: -7.0604
Max Act: 6.7791. Min Act: -0.1700
Data Index: 5997498 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0604. Min Range: -7.0604
Max Act: 6.8104. Min Act: -0.1700
Data Index: 8688250 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0604. Min Range: -7.0604
Max Act: 6.7791. Min Act: -0.1700
Data Index: 995125 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0604. Min Range: -7.0604
Max Act: 6.7791. Min Act: -0.1700
Data Index: 3825141 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0604. Min Range: -7.0604
Max Act: 6.7791. Min Act: -0.1700
Data Index: 2173047 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0604. Min Range: -7.0604
Max Act: 6.7791. Min Act: -0.1700
Data Index: 1148586 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0604. Min Range: -7.0604
Max Act: 6.7791. Min Act: -0.1700
Data Index: 2276931 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0604. Min Range: -7.0604
Max Act: 6.7479. Min Act: -0.1700
Data Index: 7319842 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0604. Min Range: -7.0604
Max Act: 6.7479. Min Act: -0.1700
Data Index: 8279544 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #19