Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3826 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8668. Min Range: -5.8668
Max Act: 5.8356. Min Act: -0.1700
Data Index: 4773050 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8668. Min Range: -5.8668
Max Act: 5.8668. Min Act: -0.1700
Data Index: 1094685 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8668. Min Range: -5.8668
Max Act: 5.8356. Min Act: -0.1700
Data Index: 3666813 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8668. Min Range: -5.8668
Max Act: 5.7418. Min Act: -0.1700
Data Index: 2502662 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8668. Min Range: -5.8668
Max Act: 5.7418. Min Act: -0.1700
Data Index: 2583418 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8668. Min Range: -5.8668
Max Act: 5.7106. Min Act: -0.1700
Data Index: 8293152 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8668. Min Range: -5.8668
Max Act: 5.7106. Min Act: -0.1700
Data Index: 4673649 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8668. Min Range: -5.8668
Max Act: 5.6793. Min Act: -0.1700
Data Index: 1094686 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8668. Min Range: -5.8668
Max Act: 5.6481. Min Act: -0.1700
Data Index: 4673651 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8668. Min Range: -5.8668
Max Act: 5.6793. Min Act: -0.1700
Data Index: 147119 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8668. Min Range: -5.8668
Max Act: 5.6168. Min Act: -0.1700
Data Index: 1094687 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8668. Min Range: -5.8668
Max Act: 5.6168. Min Act: -0.1700
Data Index: 7185952 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8668. Min Range: -5.8668
Max Act: 5.6168. Min Act: -0.1700
Data Index: 2568753 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8668. Min Range: -5.8668
Max Act: 5.6168. Min Act: -0.1700
Data Index: 228210 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8668. Min Range: -5.8668
Max Act: 5.5856. Min Act: -0.1700
Data Index: 3334134 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8668. Min Range: -5.8668
Max Act: 5.6168. Min Act: -0.1700
Data Index: 4553506 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8668. Min Range: -5.8668
Max Act: 5.5856. Min Act: -0.1700
Data Index: 5596936 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8668. Min Range: -5.8668
Max Act: 5.5543. Min Act: -0.1700
Data Index: 5414525 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8668. Min Range: -5.8668
Max Act: 5.5543. Min Act: -0.1700
Data Index: 6938335 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8668. Min Range: -5.8668
Max Act: 5.5856. Min Act: -0.1700
Data Index: 4028807 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #19