Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2154 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.9181. Min Range: -8.9181
Max Act: 8.9181. Min Act: -0.1700
Data Index: 6784885 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.9181. Min Range: -8.9181
Max Act: 8.6681. Min Act: -0.1700
Data Index: 1147062 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.9181. Min Range: -8.9181
Max Act: 8.2306. Min Act: -0.1700
Data Index: 3897166 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.9181. Min Range: -8.9181
Max Act: 8.2306. Min Act: -0.1700
Data Index: 4214571 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.9181. Min Range: -8.9181
Max Act: 8.1681. Min Act: -0.1700
Data Index: 1258721 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.9181. Min Range: -8.9181
Max Act: 8.0119. Min Act: -0.1700
Data Index: 7565078 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.9181. Min Range: -8.9181
Max Act: 7.9806. Min Act: -0.1700
Data Index: 1556029 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.9181. Min Range: -8.9181
Max Act: 7.9806. Min Act: -0.1700
Data Index: 5661352 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.9181. Min Range: -8.9181
Max Act: 7.8869. Min Act: -0.1700
Data Index: 1759898 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.9181. Min Range: -8.9181
Max Act: 7.9494. Min Act: -0.1700
Data Index: 8744774 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.9181. Min Range: -8.9181
Max Act: 7.8869. Min Act: -0.1700
Data Index: 3423682 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.9181. Min Range: -8.9181
Max Act: 7.9181. Min Act: -0.1700
Data Index: 2725166 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.9181. Min Range: -8.9181
Max Act: 7.8869. Min Act: -0.1700
Data Index: 7316435 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.9181. Min Range: -8.9181
Max Act: 7.8869. Min Act: -0.1700
Data Index: 6954341 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.9181. Min Range: -8.9181
Max Act: 7.8244. Min Act: -0.1700
Data Index: 4351310 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.9181. Min Range: -8.9181
Max Act: 7.8556. Min Act: -0.1700
Data Index: 7673671 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.9181. Min Range: -8.9181
Max Act: 7.8556. Min Act: -0.1700
Data Index: 548521 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.9181. Min Range: -8.9181
Max Act: 7.8556. Min Act: -0.1700
Data Index: 7415980 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.9181. Min Range: -8.9181
Max Act: 7.8244. Min Act: -0.1700
Data Index: 2395917 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.9181. Min Range: -8.9181
Max Act: 7.8244. Min Act: -0.1700
Data Index: 4176275 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #19