Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5514 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2888. Min Range: -5.2888
Max Act: 5.2888. Min Act: -0.1700
Data Index: 2294713 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2888. Min Range: -5.2888
Max Act: 5.1013. Min Act: -0.1700
Data Index: 7797886 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2888. Min Range: -5.2888
Max Act: 5.1013. Min Act: -0.1700
Data Index: 8063641 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2888. Min Range: -5.2888
Max Act: 5.0388. Min Act: -0.1700
Data Index: 4040984 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2888. Min Range: -5.2888
Max Act: 5.0076. Min Act: -0.1700
Data Index: 5877583 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2888. Min Range: -5.2888
Max Act: 5.0076. Min Act: -0.1700
Data Index: 3962030 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2888. Min Range: -5.2888
Max Act: 5.0076. Min Act: -0.1700
Data Index: 982676 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2888. Min Range: -5.2888
Max Act: 4.9451. Min Act: -0.1700
Data Index: 5827197 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2888. Min Range: -5.2888
Max Act: 4.9138. Min Act: -0.1700
Data Index: 3340321 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2888. Min Range: -5.2888
Max Act: 4.8826. Min Act: -0.1700
Data Index: 4555039 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2888. Min Range: -5.2888
Max Act: 4.8513. Min Act: -0.1700
Data Index: 334271 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2888. Min Range: -5.2888
Max Act: 4.8513. Min Act: -0.1700
Data Index: 654322 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2888. Min Range: -5.2888
Max Act: 4.8201. Min Act: -0.1700
Data Index: 7847433 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2888. Min Range: -5.2888
Max Act: 4.7576. Min Act: -0.1700
Data Index: 4040977 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2888. Min Range: -5.2888
Max Act: 4.8201. Min Act: -0.1700
Data Index: 4336595 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2888. Min Range: -5.2888
Max Act: 4.7888. Min Act: -0.1700
Data Index: 4693552 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2888. Min Range: -5.2888
Max Act: 4.8201. Min Act: -0.1700
Data Index: 2970026 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2888. Min Range: -5.2888
Max Act: 4.7263. Min Act: -0.1700
Data Index: 8156568 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2888. Min Range: -5.2888
Max Act: 4.7576. Min Act: -0.1700
Data Index: 7449307 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2888. Min Range: -5.2888
Max Act: 4.7263. Min Act: -0.1700
Data Index: 69075 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #19