Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1750 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.2060. Min Range: -5.2060
Max Act: 5.2060. Min Act: -0.1700
Data Index: 5155535 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2060. Min Range: -5.2060
Max Act: 5.1435. Min Act: -0.1700
Data Index: 1296758 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2060. Min Range: -5.2060
Max Act: 5.0185. Min Act: -0.1700
Data Index: 1596601 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2060. Min Range: -5.2060
Max Act: 4.9873. Min Act: -0.1700
Data Index: 6934637 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2060. Min Range: -5.2060
Max Act: 4.9560. Min Act: -0.1700
Data Index: 632932 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2060. Min Range: -5.2060
Max Act: 4.9560. Min Act: -0.1700
Data Index: 3545442 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2060. Min Range: -5.2060
Max Act: 4.9560. Min Act: -0.1700
Data Index: 7425710 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2060. Min Range: -5.2060
Max Act: 4.9560. Min Act: -0.1700
Data Index: 1514542 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2060. Min Range: -5.2060
Max Act: 4.9560. Min Act: -0.1700
Data Index: 8664923 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2060. Min Range: -5.2060
Max Act: 4.9560. Min Act: -0.1700
Data Index: 8180195 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2060. Min Range: -5.2060
Max Act: 4.9248. Min Act: -0.1700
Data Index: 2539583 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2060. Min Range: -5.2060
Max Act: 4.8935. Min Act: -0.1700
Data Index: 4952808 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2060. Min Range: -5.2060
Max Act: 4.9248. Min Act: -0.1700
Data Index: 8170106 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2060. Min Range: -5.2060
Max Act: 4.8310. Min Act: -0.1700
Data Index: 7873033 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2060. Min Range: -5.2060
Max Act: 4.8935. Min Act: -0.1700
Data Index: 8574 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2060. Min Range: -5.2060
Max Act: 4.8623. Min Act: -0.1700
Data Index: 3276763 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2060. Min Range: -5.2060
Max Act: 4.8310. Min Act: -0.1700
Data Index: 7976147 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2060. Min Range: -5.2060
Max Act: 4.8623. Min Act: -0.1700
Data Index: 3334187 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2060. Min Range: -5.2060
Max Act: 4.7685. Min Act: -0.1700
Data Index: 3700110 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2060. Min Range: -5.2060
Max Act: 4.8310. Min Act: -0.1700
Data Index: 7817412 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #19