Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 48 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6698. Min Range: -8.6698
Max Act: 8.6698. Min Act: -0.1700
Data Index: 5500640 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6698. Min Range: -8.6698
Max Act: 8.4198. Min Act: -0.1700
Data Index: 6618891 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6698. Min Range: -8.6698
Max Act: 8.2323. Min Act: -0.1700
Data Index: 4365547 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6698. Min Range: -8.6698
Max Act: 8.2323. Min Act: -0.1700
Data Index: 5580190 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6698. Min Range: -8.6698
Max Act: 8.1698. Min Act: -0.1700
Data Index: 8771847 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6698. Min Range: -8.6698
Max Act: 8.1698. Min Act: -0.1700
Data Index: 6357249 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6698. Min Range: -8.6698
Max Act: 8.0448. Min Act: -0.1700
Data Index: 2709294 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6698. Min Range: -8.6698
Max Act: 8.1073. Min Act: -0.1700
Data Index: 3939948 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6698. Min Range: -8.6698
Max Act: 8.0448. Min Act: -0.1700
Data Index: 3020647 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6698. Min Range: -8.6698
Max Act: 8.0448. Min Act: -0.1700
Data Index: 6726369 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6698. Min Range: -8.6698
Max Act: 8.0448. Min Act: -0.1700
Data Index: 5064931 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6698. Min Range: -8.6698
Max Act: 7.9823. Min Act: -0.1700
Data Index: 5038317 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6698. Min Range: -8.6698
Max Act: 7.9823. Min Act: -0.1700
Data Index: 111640 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6698. Min Range: -8.6698
Max Act: 7.9823. Min Act: -0.1700
Data Index: 841728 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6698. Min Range: -8.6698
Max Act: 7.9823. Min Act: -0.1700
Data Index: 2139325 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6698. Min Range: -8.6698
Max Act: 7.9198. Min Act: -0.1700
Data Index: 4127201 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6698. Min Range: -8.6698
Max Act: 7.9823. Min Act: -0.1700
Data Index: 1595235 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6698. Min Range: -8.6698
Max Act: 7.9823. Min Act: -0.1700
Data Index: 7443696 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6698. Min Range: -8.6698
Max Act: 7.9198. Min Act: -0.1700
Data Index: 5254775 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6698. Min Range: -8.6698
Max Act: 7.9823. Min Act: -0.1700
Data Index: 5254772 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #19