Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3806 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.1218. Min Range: -3.1218
Max Act: 3.1218. Min Act: -0.1700
Data Index: 7670390 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1218. Min Range: -3.1218
Max Act: 3.0429. Min Act: -0.1700
Data Index: 4527264 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1218. Min Range: -3.1218
Max Act: 3.0429. Min Act: -0.1700
Data Index: 1617653 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1218. Min Range: -3.1218
Max Act: 3.0271. Min Act: -0.1700
Data Index: 293332 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1218. Min Range: -3.1218
Max Act: 2.9797. Min Act: -0.1700
Data Index: 7341295 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1218. Min Range: -3.1218
Max Act: 2.9797. Min Act: -0.1700
Data Index: 1640183 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1218. Min Range: -3.1218
Max Act: 2.9639. Min Act: -0.1700
Data Index: 7032835 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1218. Min Range: -3.1218
Max Act: 2.9639. Min Act: -0.1700
Data Index: 6074628 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1218. Min Range: -3.1218
Max Act: 2.9639. Min Act: -0.1700
Data Index: 6063007 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1218. Min Range: -3.1218
Max Act: 2.9639. Min Act: -0.1700
Data Index: 1218792 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1218. Min Range: -3.1218
Max Act: 2.9639. Min Act: -0.1700
Data Index: 1139958 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1218. Min Range: -3.1218
Max Act: 2.9639. Min Act: -0.1700
Data Index: 3801614 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1218. Min Range: -3.1218
Max Act: 2.9481. Min Act: -0.1700
Data Index: 5716367 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1218. Min Range: -3.1218
Max Act: 2.9481. Min Act: -0.1700
Data Index: 8446435 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1218. Min Range: -3.1218
Max Act: 2.9481. Min Act: -0.1700
Data Index: 8180345 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1218. Min Range: -3.1218
Max Act: 2.9481. Min Act: -0.1700
Data Index: 4748100 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1218. Min Range: -3.1218
Max Act: 2.9481. Min Act: -0.1700
Data Index: 2390224 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1218. Min Range: -3.1218
Max Act: 2.9481. Min Act: -0.1700
Data Index: 3920099 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1218. Min Range: -3.1218
Max Act: 2.9481. Min Act: -0.1700
Data Index: 3637818 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1218. Min Range: -3.1218
Max Act: 2.9323. Min Act: -0.1700
Data Index: 6810719 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #19