Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2029 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0091. Min Range: -5.0091
Max Act: 5.0091. Min Act: -0.1700
Data Index: 4066064 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0091. Min Range: -5.0091
Max Act: 4.9466. Min Act: -0.1700
Data Index: 3993092 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0091. Min Range: -5.0091
Max Act: 4.9466. Min Act: -0.1700
Data Index: 7603218 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0091. Min Range: -5.0091
Max Act: 4.9153. Min Act: -0.1700
Data Index: 2957012 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0091. Min Range: -5.0091
Max Act: 4.9153. Min Act: -0.1700
Data Index: 7061408 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0091. Min Range: -5.0091
Max Act: 4.8841. Min Act: -0.1700
Data Index: 8437911 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0091. Min Range: -5.0091
Max Act: 4.9153. Min Act: -0.1700
Data Index: 3951229 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0091. Min Range: -5.0091
Max Act: 4.8841. Min Act: -0.1700
Data Index: 8513453 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0091. Min Range: -5.0091
Max Act: 4.8841. Min Act: -0.1700
Data Index: 8479948 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0091. Min Range: -5.0091
Max Act: 4.8841. Min Act: -0.1700
Data Index: 7685067 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0091. Min Range: -5.0091
Max Act: 4.8528. Min Act: -0.1700
Data Index: 4066081 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0091. Min Range: -5.0091
Max Act: 4.8841. Min Act: -0.1700
Data Index: 7527759 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0091. Min Range: -5.0091
Max Act: 4.8216. Min Act: -0.1700
Data Index: 2225898 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0091. Min Range: -5.0091
Max Act: 4.8216. Min Act: -0.1700
Data Index: 7685066 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0091. Min Range: -5.0091
Max Act: 4.8216. Min Act: -0.1700
Data Index: 6910963 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0091. Min Range: -5.0091
Max Act: 4.7903. Min Act: -0.1700
Data Index: 4066069 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0091. Min Range: -5.0091
Max Act: 4.8216. Min Act: -0.1700
Data Index: 4066079 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0091. Min Range: -5.0091
Max Act: 4.8216. Min Act: -0.1700
Data Index: 6506661 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0091. Min Range: -5.0091
Max Act: 4.7903. Min Act: -0.1700
Data Index: 2086800 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0091. Min Range: -5.0091
Max Act: 4.7903. Min Act: -0.1700
Data Index: 8155098 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #19