Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1272 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9501. Min Range: -7.9501
Max Act: 7.9501. Min Act: -0.1700
Data Index: 7546737 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9501. Min Range: -7.9501
Max Act: 7.8876. Min Act: -0.1700
Data Index: 8811677 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9501. Min Range: -7.9501
Max Act: 7.8251. Min Act: -0.1700
Data Index: 2378514 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9501. Min Range: -7.9501
Max Act: 7.8251. Min Act: -0.1700
Data Index: 909585 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9501. Min Range: -7.9501
Max Act: 7.8251. Min Act: -0.1700
Data Index: 2832849 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9501. Min Range: -7.9501
Max Act: 7.7626. Min Act: -0.1700
Data Index: 7957040 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9501. Min Range: -7.9501
Max Act: 7.7626. Min Act: -0.1700
Data Index: 1507007 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9501. Min Range: -7.9501
Max Act: 7.7001. Min Act: -0.1700
Data Index: 332693 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9501. Min Range: -7.9501
Max Act: 7.7001. Min Act: -0.1700
Data Index: 4617948 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9501. Min Range: -7.9501
Max Act: 7.7001. Min Act: -0.1700
Data Index: 80849 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9501. Min Range: -7.9501
Max Act: 7.7001. Min Act: -0.1700
Data Index: 3420119 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9501. Min Range: -7.9501
Max Act: 7.7001. Min Act: -0.1700
Data Index: 121148 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9501. Min Range: -7.9501
Max Act: 7.6376. Min Act: -0.1700
Data Index: 8178701 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9501. Min Range: -7.9501
Max Act: 7.5751. Min Act: -0.1700
Data Index: 7770389 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9501. Min Range: -7.9501
Max Act: 7.5751. Min Act: -0.1700
Data Index: 4167854 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9501. Min Range: -7.9501
Max Act: 7.5751. Min Act: -0.1700
Data Index: 8545917 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9501. Min Range: -7.9501
Max Act: 7.5439. Min Act: -0.1700
Data Index: 8069566 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9501. Min Range: -7.9501
Max Act: 7.5439. Min Act: -0.1700
Data Index: 2652046 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9501. Min Range: -7.9501
Max Act: 7.4814. Min Act: -0.1700
Data Index: 4475616 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9501. Min Range: -7.9501
Max Act: 7.5439. Min Act: -0.1700
Data Index: 2633348 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #19