Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5076 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1100. Min Range: -5.1100
Max Act: 5.1100. Min Act: -0.1700
Data Index: 8523199 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1100. Min Range: -5.1100
Max Act: 5.0163. Min Act: -0.1700
Data Index: 7879599 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1100. Min Range: -5.1100
Max Act: 5.0475. Min Act: -0.1700
Data Index: 4564784 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1100. Min Range: -5.1100
Max Act: 5.0163. Min Act: -0.1700
Data Index: 6035316 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1100. Min Range: -5.1100
Max Act: 5.0475. Min Act: -0.1700
Data Index: 5255636 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1100. Min Range: -5.1100
Max Act: 5.0475. Min Act: -0.1700
Data Index: 7264199 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1100. Min Range: -5.1100
Max Act: 4.9850. Min Act: -0.1700
Data Index: 5255631 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1100. Min Range: -5.1100
Max Act: 5.0163. Min Act: -0.1700
Data Index: 5255639 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1100. Min Range: -5.1100
Max Act: 5.0163. Min Act: -0.1700
Data Index: 5255632 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1100. Min Range: -5.1100
Max Act: 5.0163. Min Act: -0.1700
Data Index: 5255649 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1100. Min Range: -5.1100
Max Act: 5.0163. Min Act: -0.1700
Data Index: 5307092 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1100. Min Range: -5.1100
Max Act: 5.0163. Min Act: -0.1700
Data Index: 5307113 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1100. Min Range: -5.1100
Max Act: 5.0163. Min Act: -0.1700
Data Index: 5868327 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1100. Min Range: -5.1100
Max Act: 5.0163. Min Act: -0.1700
Data Index: 5868330 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1100. Min Range: -5.1100
Max Act: 5.0163. Min Act: -0.1700
Data Index: 6035302 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1100. Min Range: -5.1100
Max Act: 5.0163. Min Act: -0.1700
Data Index: 4457435 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1100. Min Range: -5.1100
Max Act: 5.0163. Min Act: -0.1700
Data Index: 953245 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1100. Min Range: -5.1100
Max Act: 4.9850. Min Act: -0.1700
Data Index: 5103892 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1100. Min Range: -5.1100
Max Act: 5.0163. Min Act: -0.1700
Data Index: 6222812 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1100. Min Range: -5.1100
Max Act: 5.0163. Min Act: -0.1700
Data Index: 953231 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #19