Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3016 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.1773. Min Range: -2.1773
Max Act: 2.1773. Min Act: -0.1700
Data Index: 3589042 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.1773. Min Range: -2.1773
Max Act: 2.1606. Min Act: -0.1700
Data Index: 6706883 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.1773. Min Range: -2.1773
Max Act: 2.1440. Min Act: -0.1700
Data Index: 4580129 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.1773. Min Range: -2.1773
Max Act: 2.1273. Min Act: -0.1700
Data Index: 728135 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.1773. Min Range: -2.1773
Max Act: 2.1106. Min Act: -0.1699
Data Index: 5140692 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.1773. Min Range: -2.1773
Max Act: 2.1106. Min Act: -0.1700
Data Index: 3783035 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.1773. Min Range: -2.1773
Max Act: 2.1106. Min Act: -0.1700
Data Index: 1142629 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.1773. Min Range: -2.1773
Max Act: 2.1106. Min Act: -0.1700
Data Index: 8430983 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.1773. Min Range: -2.1773
Max Act: 2.1106. Min Act: -0.1700
Data Index: 7220623 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.1773. Min Range: -2.1773
Max Act: 2.1106. Min Act: -0.1700
Data Index: 1503268 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.1773. Min Range: -2.1773
Max Act: 2.0938. Min Act: -0.1700
Data Index: 6128260 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.1773. Min Range: -2.1773
Max Act: 2.0938. Min Act: -0.1700
Data Index: 4655205 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.1773. Min Range: -2.1773
Max Act: 2.0771. Min Act: -0.1700
Data Index: 402500 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.1773. Min Range: -2.1773
Max Act: 2.0771. Min Act: -0.1700
Data Index: 5625922 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.1773. Min Range: -2.1773
Max Act: 2.0771. Min Act: -0.1700
Data Index: 8728455 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.1773. Min Range: -2.1773
Max Act: 2.0771. Min Act: -0.1700
Data Index: 1269218 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.1773. Min Range: -2.1773
Max Act: 2.0603. Min Act: -0.1700
Data Index: 4044244 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.1773. Min Range: -2.1773
Max Act: 2.0603. Min Act: -0.1700
Data Index: 2160354 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.1773. Min Range: -2.1773
Max Act: 2.0603. Min Act: -0.1700
Data Index: 4595097 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.1773. Min Range: -2.1773
Max Act: 2.0603. Min Act: -0.1700
Data Index: 4920432 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #19