Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2811 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.6810. Min Range: -3.6810
Max Act: 3.6810. Min Act: -0.1700
Data Index: 2312639 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6810. Min Range: -3.6810
Max Act: 3.5401. Min Act: -0.1700
Data Index: 1423015 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6810. Min Range: -3.6810
Max Act: 3.4305. Min Act: -0.1700
Data Index: 1402325 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6810. Min Range: -3.6810
Max Act: 3.3991. Min Act: -0.1700
Data Index: 7455210 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6810. Min Range: -3.6810
Max Act: 3.3678. Min Act: -0.1700
Data Index: 178145 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6810. Min Range: -3.6810
Max Act: 3.3834. Min Act: -0.1700
Data Index: 2266473 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6810. Min Range: -3.6810
Max Act: 3.3521. Min Act: -0.1700
Data Index: 6662224 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6810. Min Range: -3.6810
Max Act: 3.3364. Min Act: -0.1700
Data Index: 2747719 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6810. Min Range: -3.6810
Max Act: 3.3364. Min Act: -0.1700
Data Index: 548101 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6810. Min Range: -3.6810
Max Act: 3.3364. Min Act: -0.1700
Data Index: 5816592 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6810. Min Range: -3.6810
Max Act: 3.3207. Min Act: -0.1700
Data Index: 6258722 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6810. Min Range: -3.6810
Max Act: 3.2893. Min Act: -0.1700
Data Index: 586798 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6810. Min Range: -3.6810
Max Act: 3.2893. Min Act: -0.1700
Data Index: 5630565 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6810. Min Range: -3.6810
Max Act: 3.2579. Min Act: -0.1700
Data Index: 5516946 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6810. Min Range: -3.6810
Max Act: 3.2422. Min Act: -0.1700
Data Index: 1392924 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6810. Min Range: -3.6810
Max Act: 3.2422. Min Act: -0.1700
Data Index: 7284553 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6810. Min Range: -3.6810
Max Act: 3.2422. Min Act: -0.1700
Data Index: 4379144 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6810. Min Range: -3.6810
Max Act: 3.2265. Min Act: -0.1700
Data Index: 4372617 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6810. Min Range: -3.6810
Max Act: 3.2422. Min Act: -0.1700
Data Index: 5885010 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6810. Min Range: -3.6810
Max Act: 3.2107. Min Act: -0.1700
Data Index: 963095 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #19