Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5314 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9261. Min Range: -6.9261
Max Act: 6.9261. Min Act: -0.1700
Data Index: 1824165 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9261. Min Range: -6.9261
Max Act: 6.8949. Min Act: -0.1700
Data Index: 15002 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9261. Min Range: -6.9261
Max Act: 6.8636. Min Act: -0.1700
Data Index: 5103453 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9261. Min Range: -6.9261
Max Act: 6.8011. Min Act: -0.1700
Data Index: 1857077 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9261. Min Range: -6.9261
Max Act: 6.7699. Min Act: -0.1700
Data Index: 953861 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9261. Min Range: -6.9261
Max Act: 6.6761. Min Act: -0.1700
Data Index: 3860658 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9261. Min Range: -6.9261
Max Act: 6.6761. Min Act: -0.1700
Data Index: 5067126 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9261. Min Range: -6.9261
Max Act: 6.6761. Min Act: -0.1700
Data Index: 5220260 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9261. Min Range: -6.9261
Max Act: 6.6449. Min Act: -0.1700
Data Index: 4990935 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9261. Min Range: -6.9261
Max Act: 6.6761. Min Act: -0.1700
Data Index: 1772846 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9261. Min Range: -6.9261
Max Act: 6.6449. Min Act: -0.1700
Data Index: 221969 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9261. Min Range: -6.9261
Max Act: 6.6449. Min Act: -0.1700
Data Index: 1232829 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9261. Min Range: -6.9261
Max Act: 6.6136. Min Act: -0.1700
Data Index: 4812077 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9261. Min Range: -6.9261
Max Act: 6.6136. Min Act: -0.1700
Data Index: 4041590 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9261. Min Range: -6.9261
Max Act: 6.5511. Min Act: -0.1700
Data Index: 7512668 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9261. Min Range: -6.9261
Max Act: 6.5511. Min Act: -0.1700
Data Index: 6267117 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9261. Min Range: -6.9261
Max Act: 6.5511. Min Act: -0.1700
Data Index: 2158998 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9261. Min Range: -6.9261
Max Act: 6.5511. Min Act: -0.1700
Data Index: 2441646 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9261. Min Range: -6.9261
Max Act: 6.4886. Min Act: -0.1700
Data Index: 3723482 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9261. Min Range: -6.9261
Max Act: 6.4886. Min Act: -0.1700
Data Index: 2142450 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #19