Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2532 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6013. Min Range: -5.6013
Max Act: 5.6013. Min Act: -0.1700
Data Index: 2831276 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6013. Min Range: -5.6013
Max Act: 5.5701. Min Act: -0.1700
Data Index: 1311909 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6013. Min Range: -5.6013
Max Act: 5.5388. Min Act: -0.1700
Data Index: 2132497 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6013. Min Range: -5.6013
Max Act: 5.5076. Min Act: -0.1700
Data Index: 5964780 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6013. Min Range: -5.6013
Max Act: 5.4763. Min Act: -0.1700
Data Index: 2967969 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6013. Min Range: -5.6013
Max Act: 5.4451. Min Act: -0.1700
Data Index: 149608 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6013. Min Range: -5.6013
Max Act: 5.3513. Min Act: -0.1700
Data Index: 5756164 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6013. Min Range: -5.6013
Max Act: 5.3201. Min Act: -0.1700
Data Index: 8618459 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6013. Min Range: -5.6013
Max Act: 5.3201. Min Act: -0.1700
Data Index: 4918133 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6013. Min Range: -5.6013
Max Act: 5.3201. Min Act: -0.1700
Data Index: 8240733 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6013. Min Range: -5.6013
Max Act: 5.3201. Min Act: -0.1700
Data Index: 119436 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6013. Min Range: -5.6013
Max Act: 5.2888. Min Act: -0.1700
Data Index: 4760217 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6013. Min Range: -5.6013
Max Act: 5.2263. Min Act: -0.1700
Data Index: 2132829 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6013. Min Range: -5.6013
Max Act: 5.2576. Min Act: -0.1700
Data Index: 6981291 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6013. Min Range: -5.6013
Max Act: 5.2576. Min Act: -0.1700
Data Index: 2724789 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6013. Min Range: -5.6013
Max Act: 5.2263. Min Act: -0.1700
Data Index: 2872767 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6013. Min Range: -5.6013
Max Act: 5.2263. Min Act: -0.1700
Data Index: 4928290 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6013. Min Range: -5.6013
Max Act: 5.1951. Min Act: -0.1700
Data Index: 4874219 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6013. Min Range: -5.6013
Max Act: 5.1951. Min Act: -0.1700
Data Index: 8598006 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6013. Min Range: -5.6013
Max Act: 5.1951. Min Act: -0.1700
Data Index: 3719457 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #19