Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2729 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7272. Min Range: -5.7272
Max Act: 5.7272. Min Act: -0.1700
Data Index: 1115647 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7272. Min Range: -5.7272
Max Act: 5.6647. Min Act: -0.1700
Data Index: 5244083 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7272. Min Range: -5.7272
Max Act: 5.6647. Min Act: -0.1700
Data Index: 1275882 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7272. Min Range: -5.7272
Max Act: 5.6335. Min Act: -0.1700
Data Index: 198361 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7272. Min Range: -5.7272
Max Act: 5.5710. Min Act: -0.1700
Data Index: 5039950 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7272. Min Range: -5.7272
Max Act: 5.6022. Min Act: -0.1700
Data Index: 2896622 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7272. Min Range: -5.7272
Max Act: 5.5397. Min Act: -0.1700
Data Index: 7902100 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7272. Min Range: -5.7272
Max Act: 5.4772. Min Act: -0.1700
Data Index: 7010015 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7272. Min Range: -5.7272
Max Act: 5.4772. Min Act: -0.1700
Data Index: 6754376 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7272. Min Range: -5.7272
Max Act: 5.4460. Min Act: -0.1700
Data Index: 2175427 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7272. Min Range: -5.7272
Max Act: 5.4772. Min Act: -0.1700
Data Index: 8553668 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7272. Min Range: -5.7272
Max Act: 5.4772. Min Act: -0.1700
Data Index: 8086829 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7272. Min Range: -5.7272
Max Act: 5.4772. Min Act: -0.1700
Data Index: 2471133 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7272. Min Range: -5.7272
Max Act: 5.4147. Min Act: -0.1700
Data Index: 2436680 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7272. Min Range: -5.7272
Max Act: 5.4460. Min Act: -0.1698
Data Index: 7842936 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7272. Min Range: -5.7272
Max Act: 5.4460. Min Act: -0.1700
Data Index: 7798985 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7272. Min Range: -5.7272
Max Act: 5.4460. Min Act: -0.1700
Data Index: 825476 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7272. Min Range: -5.7272
Max Act: 5.4147. Min Act: -0.1698
Data Index: 5432964 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7272. Min Range: -5.7272
Max Act: 5.4147. Min Act: -0.1700
Data Index: 1811872 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7272. Min Range: -5.7272
Max Act: 5.4147. Min Act: -0.1700
Data Index: 4989441 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #19