Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2958 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9619. Min Range: -7.9619
Max Act: 7.9619. Min Act: -0.1700
Data Index: 1010831 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9619. Min Range: -7.9619
Max Act: 7.8369. Min Act: -0.1700
Data Index: 6455794 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9619. Min Range: -7.9619
Max Act: 7.8369. Min Act: -0.1700
Data Index: 4732604 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9619. Min Range: -7.9619
Max Act: 7.8369. Min Act: -0.1700
Data Index: 6797457 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9619. Min Range: -7.9619
Max Act: 7.8369. Min Act: -0.1700
Data Index: 6943454 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9619. Min Range: -7.9619
Max Act: 7.8369. Min Act: -0.1700
Data Index: 4657435 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9619. Min Range: -7.9619
Max Act: 7.7119. Min Act: -0.1700
Data Index: 6067827 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9619. Min Range: -7.9619
Max Act: 7.7119. Min Act: -0.1700
Data Index: 7476644 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9619. Min Range: -7.9619
Max Act: 7.6494. Min Act: -0.1700
Data Index: 4172287 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9619. Min Range: -7.9619
Max Act: 7.6494. Min Act: -0.1700
Data Index: 2869878 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9619. Min Range: -7.9619
Max Act: 7.5869. Min Act: -0.1700
Data Index: 2861622 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9619. Min Range: -7.9619
Max Act: 7.6494. Min Act: -0.1700
Data Index: 2557602 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9619. Min Range: -7.9619
Max Act: 7.6181. Min Act: -0.1700
Data Index: 4135498 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9619. Min Range: -7.9619
Max Act: 7.5869. Min Act: -0.1700
Data Index: 7424630 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9619. Min Range: -7.9619
Max Act: 7.5556. Min Act: -0.1700
Data Index: 6055273 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9619. Min Range: -7.9619
Max Act: 7.5556. Min Act: -0.1700
Data Index: 5848958 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9619. Min Range: -7.9619
Max Act: 7.5556. Min Act: -0.1700
Data Index: 6415971 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9619. Min Range: -7.9619
Max Act: 7.5244. Min Act: -0.1700
Data Index: 5527279 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9619. Min Range: -7.9619
Max Act: 7.5556. Min Act: -0.1700
Data Index: 4481150 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9619. Min Range: -7.9619
Max Act: 7.5244. Min Act: -0.1700
Data Index: 258761 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #19