Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2946 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4827. Min Range: -6.4827
Max Act: 6.4827. Min Act: -0.1700
Data Index: 7450281 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4827. Min Range: -6.4827
Max Act: 6.1077. Min Act: -0.1700
Data Index: 320202 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4827. Min Range: -6.4827
Max Act: 5.9515. Min Act: -0.1700
Data Index: 6686304 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4827. Min Range: -6.4827
Max Act: 5.8890. Min Act: -0.1700
Data Index: 1849782 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4827. Min Range: -6.4827
Max Act: 5.7952. Min Act: -0.1700
Data Index: 642848 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4827. Min Range: -6.4827
Max Act: 5.7952. Min Act: -0.1700
Data Index: 6092059 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4827. Min Range: -6.4827
Max Act: 5.7952. Min Act: -0.1700
Data Index: 4555793 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4827. Min Range: -6.4827
Max Act: 5.7327. Min Act: -0.1700
Data Index: 8550429 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4827. Min Range: -6.4827
Max Act: 5.6390. Min Act: -0.1700
Data Index: 7468363 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4827. Min Range: -6.4827
Max Act: 5.6390. Min Act: -0.1700
Data Index: 1599468 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4827. Min Range: -6.4827
Max Act: 5.6077. Min Act: -0.1700
Data Index: 4758794 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4827. Min Range: -6.4827
Max Act: 5.5765. Min Act: -0.1700
Data Index: 7458469 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4827. Min Range: -6.4827
Max Act: 5.5765. Min Act: -0.1700
Data Index: 6021344 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4827. Min Range: -6.4827
Max Act: 5.5452. Min Act: -0.1700
Data Index: 6514373 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4827. Min Range: -6.4827
Max Act: 5.5452. Min Act: -0.1700
Data Index: 8570207 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4827. Min Range: -6.4827
Max Act: 5.5452. Min Act: -0.1700
Data Index: 2516805 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4827. Min Range: -6.4827
Max Act: 5.5140. Min Act: -0.1700
Data Index: 1430372 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4827. Min Range: -6.4827
Max Act: 5.5140. Min Act: -0.1700
Data Index: 3563380 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4827. Min Range: -6.4827
Max Act: 5.5140. Min Act: -0.1700
Data Index: 1447960 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4827. Min Range: -6.4827
Max Act: 5.5140. Min Act: -0.1700
Data Index: 8175811 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #19