Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1360 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1181. Min Range: -6.1181
Max Act: 6.1181. Min Act: -0.1700
Data Index: 1428317 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1181. Min Range: -6.1181
Max Act: 6.1181. Min Act: -0.1700
Data Index: 52404 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1181. Min Range: -6.1181
Max Act: 6.0868. Min Act: -0.1700
Data Index: 4106661 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1181. Min Range: -6.1181
Max Act: 5.9306. Min Act: -0.1700
Data Index: 2246752 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1181. Min Range: -6.1181
Max Act: 5.9306. Min Act: -0.1700
Data Index: 6906331 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1181. Min Range: -6.1181
Max Act: 5.9306. Min Act: -0.1700
Data Index: 6541644 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1181. Min Range: -6.1181
Max Act: 5.9306. Min Act: -0.1700
Data Index: 4601080 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1181. Min Range: -6.1181
Max Act: 5.8993. Min Act: -0.1700
Data Index: 7679670 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1181. Min Range: -6.1181
Max Act: 5.8993. Min Act: -0.1700
Data Index: 3242515 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1181. Min Range: -6.1181
Max Act: 5.8681. Min Act: -0.1700
Data Index: 4601076 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1181. Min Range: -6.1181
Max Act: 5.8681. Min Act: -0.1700
Data Index: 2776439 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1181. Min Range: -6.1181
Max Act: 5.8056. Min Act: -0.1700
Data Index: 6926036 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1181. Min Range: -6.1181
Max Act: 5.8056. Min Act: -0.1700
Data Index: 5720604 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1181. Min Range: -6.1181
Max Act: 5.7743. Min Act: -0.1700
Data Index: 4475942 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1181. Min Range: -6.1181
Max Act: 5.8056. Min Act: -0.1700
Data Index: 5452016 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1181. Min Range: -6.1181
Max Act: 5.7743. Min Act: -0.1700
Data Index: 4378060 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1181. Min Range: -6.1181
Max Act: 5.7431. Min Act: -0.1700
Data Index: 7829010 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1181. Min Range: -6.1181
Max Act: 5.7743. Min Act: -0.1700
Data Index: 6254542 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1181. Min Range: -6.1181
Max Act: 5.7743. Min Act: -0.1700
Data Index: 5825632 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1181. Min Range: -6.1181
Max Act: 5.7431. Min Act: -0.1700
Data Index: 3940889 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #19