Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3032 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.3163. Min Range: -3.3163
Max Act: 3.3163. Min Act: -0.1700
Data Index: 7925202 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3163. Min Range: -3.3163
Max Act: 3.3163. Min Act: -0.1700
Data Index: 5048406 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3163. Min Range: -3.3163
Max Act: 3.2064. Min Act: -0.1700
Data Index: 4124066 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3163. Min Range: -3.3163
Max Act: 3.1907. Min Act: -0.1700
Data Index: 1957899 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3163. Min Range: -3.3163
Max Act: 3.1749. Min Act: -0.1700
Data Index: 5643106 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3163. Min Range: -3.3163
Max Act: 3.1592. Min Act: -0.1700
Data Index: 2019593 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3163. Min Range: -3.3163
Max Act: 3.1592. Min Act: -0.1700
Data Index: 6255629 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3163. Min Range: -3.3163
Max Act: 3.1277. Min Act: -0.1700
Data Index: 2142829 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3163. Min Range: -3.3163
Max Act: 3.1277. Min Act: -0.1700
Data Index: 3543944 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3163. Min Range: -3.3163
Max Act: 3.1119. Min Act: -0.1700
Data Index: 394885 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3163. Min Range: -3.3163
Max Act: 3.1434. Min Act: -0.1700
Data Index: 6054505 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3163. Min Range: -3.3163
Max Act: 3.0962. Min Act: -0.1700
Data Index: 4759298 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3163. Min Range: -3.3163
Max Act: 3.1119. Min Act: -0.1700
Data Index: 6353503 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3163. Min Range: -3.3163
Max Act: 3.1119. Min Act: -0.1700
Data Index: 993495 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3163. Min Range: -3.3163
Max Act: 3.0962. Min Act: -0.1700
Data Index: 8609839 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3163. Min Range: -3.3163
Max Act: 3.0804. Min Act: -0.1700
Data Index: 8594244 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3163. Min Range: -3.3163
Max Act: 3.0962. Min Act: -0.1700
Data Index: 5262048 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3163. Min Range: -3.3163
Max Act: 3.0962. Min Act: -0.1700
Data Index: 8208021 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3163. Min Range: -3.3163
Max Act: 3.0962. Min Act: -0.1700
Data Index: 5686730 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3163. Min Range: -3.3163
Max Act: 3.0804. Min Act: -0.1700
Data Index: 3815913 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #19