Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1581 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.1019. Min Range: -4.1019
Max Act: 4.1019. Min Act: -0.1700
Data Index: 402210 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1019. Min Range: -4.1019
Max Act: 4.0707. Min Act: -0.1700
Data Index: 1505879 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1019. Min Range: -4.1019
Max Act: 4.0707. Min Act: -0.1700
Data Index: 2853690 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1019. Min Range: -4.1019
Max Act: 4.0707. Min Act: -0.1700
Data Index: 1516241 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1019. Min Range: -4.1019
Max Act: 4.0394. Min Act: -0.1700
Data Index: 4918707 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1019. Min Range: -4.1019
Max Act: 4.0394. Min Act: -0.1700
Data Index: 2989587 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1019. Min Range: -4.1019
Max Act: 4.0394. Min Act: -0.1700
Data Index: 8779311 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1019. Min Range: -4.1019
Max Act: 4.0394. Min Act: -0.1700
Data Index: 3541766 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1019. Min Range: -4.1019
Max Act: 4.0394. Min Act: -0.1700
Data Index: 6542906 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1019. Min Range: -4.1019
Max Act: 4.0394. Min Act: -0.1700
Data Index: 4230548 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1019. Min Range: -4.1019
Max Act: 4.0082. Min Act: -0.1700
Data Index: 2853687 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1019. Min Range: -4.1019
Max Act: 4.0082. Min Act: -0.1700
Data Index: 6985755 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1019. Min Range: -4.1019
Max Act: 4.0082. Min Act: -0.1700
Data Index: 2419535 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1019. Min Range: -4.1019
Max Act: 4.0082. Min Act: -0.1700
Data Index: 6292243 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1019. Min Range: -4.1019
Max Act: 3.9769. Min Act: -0.1700
Data Index: 3249071 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1019. Min Range: -4.1019
Max Act: 4.0082. Min Act: -0.1700
Data Index: 7542958 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1019. Min Range: -4.1019
Max Act: 4.0082. Min Act: -0.1700
Data Index: 2989654 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1019. Min Range: -4.1019
Max Act: 3.9769. Min Act: -0.1700
Data Index: 6707984 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1019. Min Range: -4.1019
Max Act: 3.9769. Min Act: -0.1700
Data Index: 2522221 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1019. Min Range: -4.1019
Max Act: 3.9769. Min Act: -0.1700
Data Index: 7259892 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #19