Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3198 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3888. Min Range: -5.3888
Max Act: 5.3888. Min Act: -0.1700
Data Index: 5948974 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3888. Min Range: -5.3888
Max Act: 5.0451. Min Act: -0.1700
Data Index: 5948975 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3888. Min Range: -5.3888
Max Act: 5.0451. Min Act: -0.1700
Data Index: 6295619 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3888. Min Range: -5.3888
Max Act: 4.9513. Min Act: -0.1700
Data Index: 3967863 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3888. Min Range: -5.3888
Max Act: 4.9513. Min Act: -0.1700
Data Index: 7054659 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3888. Min Range: -5.3888
Max Act: 4.9513. Min Act: -0.1700
Data Index: 4703319 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3888. Min Range: -5.3888
Max Act: 4.8576. Min Act: -0.1700
Data Index: 559079 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3888. Min Range: -5.3888
Max Act: 4.8576. Min Act: -0.1700
Data Index: 6269121 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3888. Min Range: -5.3888
Max Act: 4.8576. Min Act: -0.1700
Data Index: 4993969 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3888. Min Range: -5.3888
Max Act: 4.8263. Min Act: -0.1700
Data Index: 8710557 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3888. Min Range: -5.3888
Max Act: 4.8263. Min Act: -0.1700
Data Index: 74165 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3888. Min Range: -5.3888
Max Act: 4.8263. Min Act: -0.1700
Data Index: 2045939 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3888. Min Range: -5.3888
Max Act: 4.8263. Min Act: -0.1700
Data Index: 1797738 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3888. Min Range: -5.3888
Max Act: 4.8576. Min Act: -0.1700
Data Index: 2520268 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3888. Min Range: -5.3888
Max Act: 4.8263. Min Act: -0.1700
Data Index: 2910158 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3888. Min Range: -5.3888
Max Act: 4.8263. Min Act: -0.1700
Data Index: 3606965 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3888. Min Range: -5.3888
Max Act: 4.8263. Min Act: -0.1700
Data Index: 6974077 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3888. Min Range: -5.3888
Max Act: 4.7951. Min Act: -0.1700
Data Index: 2765186 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3888. Min Range: -5.3888
Max Act: 4.7951. Min Act: -0.1700
Data Index: 2559374 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3888. Min Range: -5.3888
Max Act: 4.7638. Min Act: -0.1700
Data Index: 6781436 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #19