Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4191 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2532. Min Range: -6.2532
Max Act: 6.2532. Min Act: -0.1700
Data Index: 2854702 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2532. Min Range: -6.2532
Max Act: 6.0970. Min Act: -0.1700
Data Index: 273283 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2532. Min Range: -6.2532
Max Act: 6.0032. Min Act: -0.1700
Data Index: 8062215 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2532. Min Range: -6.2532
Max Act: 6.0032. Min Act: -0.1700
Data Index: 5490052 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2532. Min Range: -6.2532
Max Act: 5.9407. Min Act: -0.1700
Data Index: 7371442 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2532. Min Range: -6.2532
Max Act: 5.9407. Min Act: -0.1700
Data Index: 7928377 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2532. Min Range: -6.2532
Max Act: 5.9095. Min Act: -0.1700
Data Index: 960718 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2532. Min Range: -6.2532
Max Act: 5.9407. Min Act: -0.1700
Data Index: 1961071 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2532. Min Range: -6.2532
Max Act: 5.8782. Min Act: -0.1700
Data Index: 6381485 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2532. Min Range: -6.2532
Max Act: 5.8470. Min Act: -0.1700
Data Index: 1380118 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2532. Min Range: -6.2532
Max Act: 5.8470. Min Act: -0.1700
Data Index: 6150573 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2532. Min Range: -6.2532
Max Act: 5.7845. Min Act: -0.1700
Data Index: 1534985 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2532. Min Range: -6.2532
Max Act: 5.7532. Min Act: -0.1700
Data Index: 2077247 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2532. Min Range: -6.2532
Max Act: 5.7532. Min Act: -0.1700
Data Index: 1351480 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2532. Min Range: -6.2532
Max Act: 5.7220. Min Act: -0.1700
Data Index: 1762254 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2532. Min Range: -6.2532
Max Act: 5.7532. Min Act: -0.1700
Data Index: 8201645 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2532. Min Range: -6.2532
Max Act: 5.7532. Min Act: -0.1700
Data Index: 7155868 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2532. Min Range: -6.2532
Max Act: 5.7220. Min Act: -0.1700
Data Index: 485132 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2532. Min Range: -6.2532
Max Act: 5.7220. Min Act: -0.1700
Data Index: 6625605 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2532. Min Range: -6.2532
Max Act: 5.7220. Min Act: -0.1700
Data Index: 4850933 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #19