Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4321 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.8483. Min Range: -4.8483
Max Act: 4.8483. Min Act: -0.1700
Data Index: 5906491 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8483. Min Range: -4.8483
Max Act: 4.7858. Min Act: -0.1700
Data Index: 5798311 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8483. Min Range: -4.8483
Max Act: 4.7233. Min Act: -0.1700
Data Index: 255098 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8483. Min Range: -4.8483
Max Act: 4.7233. Min Act: -0.1700
Data Index: 2129438 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8483. Min Range: -4.8483
Max Act: 4.7233. Min Act: -0.1700
Data Index: 6185436 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8483. Min Range: -4.8483
Max Act: 4.7233. Min Act: -0.1700
Data Index: 917912 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8483. Min Range: -4.8483
Max Act: 4.6608. Min Act: -0.1700
Data Index: 5226168 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8483. Min Range: -4.8483
Max Act: 4.6608. Min Act: -0.1700
Data Index: 7283923 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8483. Min Range: -4.8483
Max Act: 4.6608. Min Act: -0.1700
Data Index: 2774143 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8483. Min Range: -4.8483
Max Act: 4.6608. Min Act: -0.1700
Data Index: 3233892 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8483. Min Range: -4.8483
Max Act: 4.6296. Min Act: -0.1700
Data Index: 342026 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8483. Min Range: -4.8483
Max Act: 4.6296. Min Act: -0.1700
Data Index: 7753353 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8483. Min Range: -4.8483
Max Act: 4.6296. Min Act: -0.1700
Data Index: 8718114 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8483. Min Range: -4.8483
Max Act: 4.6296. Min Act: -0.1700
Data Index: 1399558 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8483. Min Range: -4.8483
Max Act: 4.6296. Min Act: -0.1700
Data Index: 5618876 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8483. Min Range: -4.8483
Max Act: 4.6296. Min Act: -0.1700
Data Index: 5549225 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8483. Min Range: -4.8483
Max Act: 4.6296. Min Act: -0.1700
Data Index: 7903094 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8483. Min Range: -4.8483
Max Act: 4.5983. Min Act: -0.1700
Data Index: 8800818 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8483. Min Range: -4.8483
Max Act: 4.5671. Min Act: -0.1700
Data Index: 1231299 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8483. Min Range: -4.8483
Max Act: 4.5671. Min Act: -0.1700
Data Index: 4548851 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #19