Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4981 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.4702. Min Range: -4.4702
Max Act: 4.4702. Min Act: -0.1700
Data Index: 3779672 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4702. Min Range: -4.4702
Max Act: 4.4077. Min Act: -0.1700
Data Index: 1600453 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4702. Min Range: -4.4702
Max Act: 4.3452. Min Act: -0.1700
Data Index: 1993805 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4702. Min Range: -4.4702
Max Act: 4.2827. Min Act: -0.1700
Data Index: 6542171 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4702. Min Range: -4.4702
Max Act: 4.3139. Min Act: -0.1700
Data Index: 1388915 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4702. Min Range: -4.4702
Max Act: 4.2514. Min Act: -0.1700
Data Index: 8018962 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4702. Min Range: -4.4702
Max Act: 4.2827. Min Act: -0.1700
Data Index: 4108326 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4702. Min Range: -4.4702
Max Act: 4.2827. Min Act: -0.1700
Data Index: 278168 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4702. Min Range: -4.4702
Max Act: 4.2514. Min Act: -0.1700
Data Index: 4332965 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4702. Min Range: -4.4702
Max Act: 4.2514. Min Act: -0.1700
Data Index: 5158541 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4702. Min Range: -4.4702
Max Act: 4.2514. Min Act: -0.1700
Data Index: 6110584 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4702. Min Range: -4.4702
Max Act: 4.2202. Min Act: -0.1700
Data Index: 2345434 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4702. Min Range: -4.4702
Max Act: 4.2202. Min Act: -0.1700
Data Index: 1588320 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4702. Min Range: -4.4702
Max Act: 4.2202. Min Act: -0.1700
Data Index: 5958229 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4702. Min Range: -4.4702
Max Act: 4.2202. Min Act: -0.1700
Data Index: 5579830 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4702. Min Range: -4.4702
Max Act: 4.2202. Min Act: -0.1700
Data Index: 5557740 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4702. Min Range: -4.4702
Max Act: 4.2202. Min Act: -0.1700
Data Index: 700501 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4702. Min Range: -4.4702
Max Act: 4.1889. Min Act: -0.1700
Data Index: 929398 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4702. Min Range: -4.4702
Max Act: 4.1889. Min Act: -0.1700
Data Index: 3085822 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4702. Min Range: -4.4702
Max Act: 4.2202. Min Act: -0.1700
Data Index: 3873090 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #19