Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2973 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1919. Min Range: -6.1919
Max Act: 6.1919. Min Act: -0.1700
Data Index: 6817325 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1919. Min Range: -6.1919
Max Act: 6.1606. Min Act: -0.1700
Data Index: 8176435 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1919. Min Range: -6.1919
Max Act: 6.1294. Min Act: -0.1700
Data Index: 453153 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1919. Min Range: -6.1919
Max Act: 6.0981. Min Act: -0.1700
Data Index: 5884272 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1919. Min Range: -6.1919
Max Act: 6.0669. Min Act: -0.1700
Data Index: 5383299 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1919. Min Range: -6.1919
Max Act: 6.0356. Min Act: -0.1700
Data Index: 5794307 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1919. Min Range: -6.1919
Max Act: 6.0044. Min Act: -0.1700
Data Index: 1273291 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1919. Min Range: -6.1919
Max Act: 6.0356. Min Act: -0.1700
Data Index: 1457438 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1919. Min Range: -6.1919
Max Act: 6.0044. Min Act: -0.1700
Data Index: 3478827 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1919. Min Range: -6.1919
Max Act: 6.0044. Min Act: -0.1700
Data Index: 5454963 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1919. Min Range: -6.1919
Max Act: 5.9419. Min Act: -0.1700
Data Index: 444212 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1919. Min Range: -6.1919
Max Act: 5.9419. Min Act: -0.1700
Data Index: 2521047 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1919. Min Range: -6.1919
Max Act: 5.9106. Min Act: -0.1700
Data Index: 4122769 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1919. Min Range: -6.1919
Max Act: 5.9419. Min Act: -0.1700
Data Index: 2424272 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1919. Min Range: -6.1919
Max Act: 5.9419. Min Act: -0.1700
Data Index: 8591024 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1919. Min Range: -6.1919
Max Act: 5.9419. Min Act: -0.1700
Data Index: 3036437 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1919. Min Range: -6.1919
Max Act: 5.9419. Min Act: -0.1700
Data Index: 4878309 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1919. Min Range: -6.1919
Max Act: 5.9106. Min Act: -0.1700
Data Index: 6668531 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1919. Min Range: -6.1919
Max Act: 5.9106. Min Act: -0.1700
Data Index: 445848 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1919. Min Range: -6.1919
Max Act: 5.9106. Min Act: -0.1700
Data Index: 1197869 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #19