Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 226 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.0367. Min Range: -1.0367
Max Act: 1.0367. Min Act: -0.1700
Data Index: 5363621 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.0367. Min Range: -1.0367
Max Act: 1.0193. Min Act: -0.1700
Data Index: 168569 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.0367. Min Range: -1.0367
Max Act: 1.0280. Min Act: -0.1700
Data Index: 8793938 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.0367. Min Range: -1.0367
Max Act: 1.0106. Min Act: -0.1700
Data Index: 3416975 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.0367. Min Range: -1.0367
Max Act: 1.0106. Min Act: -0.1700
Data Index: 729213 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.0367. Min Range: -1.0367
Max Act: 1.0106. Min Act: -0.1700
Data Index: 570701 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.0367. Min Range: -1.0367
Max Act: 1.0019. Min Act: -0.1700
Data Index: 3391682 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.0367. Min Range: -1.0367
Max Act: 1.0019. Min Act: -0.1700
Data Index: 7899559 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.0367. Min Range: -1.0367
Max Act: 1.0019. Min Act: -0.1700
Data Index: 7226555 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.0367. Min Range: -1.0367
Max Act: 0.9933. Min Act: -0.1700
Data Index: 8756441 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.0367. Min Range: -1.0367
Max Act: 0.9933. Min Act: -0.1700
Data Index: 134785 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.0367. Min Range: -1.0367
Max Act: 0.9846. Min Act: -0.1700
Data Index: 8341610 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.0367. Min Range: -1.0367
Max Act: 0.9846. Min Act: -0.1700
Data Index: 4482850 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.0367. Min Range: -1.0367
Max Act: 0.9846. Min Act: -0.1700
Data Index: 4676724 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.0367. Min Range: -1.0367
Max Act: 0.9846. Min Act: -0.1700
Data Index: 5088832 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.0367. Min Range: -1.0367
Max Act: 0.9933. Min Act: -0.1700
Data Index: 5344352 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.0367. Min Range: -1.0367
Max Act: 0.9846. Min Act: -0.1700
Data Index: 8793937 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.0367. Min Range: -1.0367
Max Act: 0.9846. Min Act: -0.1700
Data Index: 6495875 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.0367. Min Range: -1.0367
Max Act: 0.9846. Min Act: -0.1700
Data Index: 6612616 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.0367. Min Range: -1.0367
Max Act: 0.9673. Min Act: -0.1700
Data Index: 6492361 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #19