Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2972 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.0682. Min Range: -3.0682
Max Act: 3.0682. Min Act: -0.1700
Data Index: 444380 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0682. Min Range: -3.0682
Max Act: 3.0682. Min Act: -0.1700
Data Index: 2953501 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0682. Min Range: -3.0682
Max Act: 3.0524. Min Act: -0.1700
Data Index: 8371359 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0682. Min Range: -3.0682
Max Act: 3.0366. Min Act: -0.1700
Data Index: 5668120 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0682. Min Range: -3.0682
Max Act: 3.0366. Min Act: -0.1700
Data Index: 8502916 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0682. Min Range: -3.0682
Max Act: 3.0366. Min Act: -0.1700
Data Index: 8754143 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0682. Min Range: -3.0682
Max Act: 2.9893. Min Act: -0.1700
Data Index: 3831566 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0682. Min Range: -3.0682
Max Act: 3.0051. Min Act: -0.1700
Data Index: 5271882 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0682. Min Range: -3.0682
Max Act: 3.0051. Min Act: -0.1700
Data Index: 1891886 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0682. Min Range: -3.0682
Max Act: 2.9734. Min Act: -0.1700
Data Index: 8658630 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0682. Min Range: -3.0682
Max Act: 2.9576. Min Act: -0.1700
Data Index: 4417524 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0682. Min Range: -3.0682
Max Act: 2.9259. Min Act: -0.1700
Data Index: 6240239 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0682. Min Range: -3.0682
Max Act: 2.9259. Min Act: -0.1700
Data Index: 1720674 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0682. Min Range: -3.0682
Max Act: 2.9418. Min Act: -0.1699
Data Index: 7385668 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0682. Min Range: -3.0682
Max Act: 2.9259. Min Act: -0.1700
Data Index: 2448389 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0682. Min Range: -3.0682
Max Act: 2.9101. Min Act: -0.1700
Data Index: 6916050 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0682. Min Range: -3.0682
Max Act: 2.8942. Min Act: -0.1700
Data Index: 6635209 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0682. Min Range: -3.0682
Max Act: 2.9101. Min Act: -0.1700
Data Index: 5609743 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0682. Min Range: -3.0682
Max Act: 2.8942. Min Act: -0.1700
Data Index: 7017917 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0682. Min Range: -3.0682
Max Act: 2.8784. Min Act: -0.1700
Data Index: 202381 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #19