Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3051 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8654. Min Range: -3.8654
Max Act: 3.8654. Min Act: -0.1700
Data Index: 57650 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8654. Min Range: -3.8654
Max Act: 3.8341. Min Act: -0.1700
Data Index: 3756465 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8654. Min Range: -3.8654
Max Act: 3.8029. Min Act: -0.1700
Data Index: 8732472 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8654. Min Range: -3.8654
Max Act: 3.7403. Min Act: -0.1700
Data Index: 7886916 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8654. Min Range: -3.8654
Max Act: 3.7716. Min Act: -0.1700
Data Index: 1892956 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8654. Min Range: -3.8654
Max Act: 3.7403. Min Act: -0.1700
Data Index: 2838975 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8654. Min Range: -3.8654
Max Act: 3.7403. Min Act: -0.1700
Data Index: 1532705 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8654. Min Range: -3.8654
Max Act: 3.7403. Min Act: -0.1700
Data Index: 8443045 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8654. Min Range: -3.8654
Max Act: 3.7090. Min Act: -0.1700
Data Index: 8517456 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8654. Min Range: -3.8654
Max Act: 3.6777. Min Act: -0.1700
Data Index: 4655905 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8654. Min Range: -3.8654
Max Act: 3.6777. Min Act: -0.1700
Data Index: 6800607 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8654. Min Range: -3.8654
Max Act: 3.6777. Min Act: -0.1700
Data Index: 2479820 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8654. Min Range: -3.8654
Max Act: 3.6777. Min Act: -0.1700
Data Index: 495433 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8654. Min Range: -3.8654
Max Act: 3.6777. Min Act: -0.1700
Data Index: 5149357 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8654. Min Range: -3.8654
Max Act: 3.6777. Min Act: -0.1700
Data Index: 7839181 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8654. Min Range: -3.8654
Max Act: 3.6777. Min Act: -0.1700
Data Index: 7839183 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8654. Min Range: -3.8654
Max Act: 3.6465. Min Act: -0.1700
Data Index: 2141905 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8654. Min Range: -3.8654
Max Act: 3.6152. Min Act: -0.1700
Data Index: 6324553 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8654. Min Range: -3.8654
Max Act: 3.6465. Min Act: -0.1700
Data Index: 3756466 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8654. Min Range: -3.8654
Max Act: 3.6465. Min Act: -0.1700
Data Index: 1532703 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #19