Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5034 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1480. Min Range: -5.1480
Max Act: 5.1480. Min Act: -0.1700
Data Index: 2993536 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1480. Min Range: -5.1480
Max Act: 5.0542. Min Act: -0.1700
Data Index: 5007795 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1480. Min Range: -5.1480
Max Act: 5.0542. Min Act: -0.1700
Data Index: 4275860 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1480. Min Range: -5.1480
Max Act: 5.0230. Min Act: -0.1700
Data Index: 309926 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1480. Min Range: -5.1480
Max Act: 5.0230. Min Act: -0.1700
Data Index: 2497151 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1480. Min Range: -5.1480
Max Act: 5.0230. Min Act: -0.1700
Data Index: 767236 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1480. Min Range: -5.1480
Max Act: 4.9917. Min Act: -0.1700
Data Index: 4661047 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1480. Min Range: -5.1480
Max Act: 4.9917. Min Act: -0.1700
Data Index: 4223887 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1480. Min Range: -5.1480
Max Act: 4.9917. Min Act: -0.1700
Data Index: 1941313 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1480. Min Range: -5.1480
Max Act: 4.9917. Min Act: -0.1700
Data Index: 1921576 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1480. Min Range: -5.1480
Max Act: 4.9917. Min Act: -0.1700
Data Index: 4666296 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1480. Min Range: -5.1480
Max Act: 4.9917. Min Act: -0.1700
Data Index: 3895462 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1480. Min Range: -5.1480
Max Act: 4.9917. Min Act: -0.1700
Data Index: 4281662 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1480. Min Range: -5.1480
Max Act: 4.9917. Min Act: -0.1700
Data Index: 6650681 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1480. Min Range: -5.1480
Max Act: 4.9917. Min Act: -0.1700
Data Index: 1127975 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1480. Min Range: -5.1480
Max Act: 4.9605. Min Act: -0.1700
Data Index: 2965337 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1480. Min Range: -5.1480
Max Act: 4.9917. Min Act: -0.1700
Data Index: 4505538 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1480. Min Range: -5.1480
Max Act: 4.9605. Min Act: -0.1700
Data Index: 4857755 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1480. Min Range: -5.1480
Max Act: 4.9917. Min Act: -0.1700
Data Index: 3914712 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1480. Min Range: -5.1480
Max Act: 4.9605. Min Act: -0.1700
Data Index: 520566 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #19