Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 734 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6793. Min Range: -6.6793
Max Act: 6.6793. Min Act: -0.1700
Data Index: 773769 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6793. Min Range: -6.6793
Max Act: 6.6480. Min Act: -0.1700
Data Index: 936202 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6793. Min Range: -6.6793
Max Act: 6.6168. Min Act: -0.1700
Data Index: 7803470 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6793. Min Range: -6.6793
Max Act: 6.5230. Min Act: -0.1700
Data Index: 8798233 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6793. Min Range: -6.6793
Max Act: 6.4293. Min Act: -0.1700
Data Index: 4004190 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6793. Min Range: -6.6793
Max Act: 6.4293. Min Act: -0.1700
Data Index: 2584910 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6793. Min Range: -6.6793
Max Act: 6.3668. Min Act: -0.1700
Data Index: 7146870 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6793. Min Range: -6.6793
Max Act: 6.3668. Min Act: -0.1700
Data Index: 4500922 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6793. Min Range: -6.6793
Max Act: 6.3355. Min Act: -0.1700
Data Index: 5385797 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6793. Min Range: -6.6793
Max Act: 6.3355. Min Act: -0.1700
Data Index: 4182001 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6793. Min Range: -6.6793
Max Act: 6.3355. Min Act: -0.1700
Data Index: 2446790 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6793. Min Range: -6.6793
Max Act: 6.3043. Min Act: -0.1700
Data Index: 8636493 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6793. Min Range: -6.6793
Max Act: 6.3043. Min Act: -0.1700
Data Index: 7838816 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6793. Min Range: -6.6793
Max Act: 6.3043. Min Act: -0.1700
Data Index: 8194529 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6793. Min Range: -6.6793
Max Act: 6.2730. Min Act: -0.1700
Data Index: 7387913 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6793. Min Range: -6.6793
Max Act: 6.2730. Min Act: -0.1700
Data Index: 6850584 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6793. Min Range: -6.6793
Max Act: 6.2730. Min Act: -0.1700
Data Index: 8798232 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6793. Min Range: -6.6793
Max Act: 6.2730. Min Act: -0.1700
Data Index: 5401943 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6793. Min Range: -6.6793
Max Act: 6.2105. Min Act: -0.1700
Data Index: 3657073 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6793. Min Range: -6.6793
Max Act: 6.2105. Min Act: -0.1700
Data Index: 355731 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #19