Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4231 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2154. Min Range: -5.2154
Max Act: 5.1842. Min Act: -0.1700
Data Index: 5542010 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2154. Min Range: -5.2154
Max Act: 5.1842. Min Act: -0.1700
Data Index: 997482 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2154. Min Range: -5.2154
Max Act: 5.2154. Min Act: -0.1700
Data Index: 5585332 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2154. Min Range: -5.2154
Max Act: 5.1842. Min Act: -0.1700
Data Index: 2497481 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2154. Min Range: -5.2154
Max Act: 5.1529. Min Act: -0.1700
Data Index: 5935187 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2154. Min Range: -5.2154
Max Act: 5.0904. Min Act: -0.1700
Data Index: 6153499 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2154. Min Range: -5.2154
Max Act: 5.0592. Min Act: -0.1700
Data Index: 7506120 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2154. Min Range: -5.2154
Max Act: 5.0592. Min Act: -0.1700
Data Index: 4176767 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2154. Min Range: -5.2154
Max Act: 5.0592. Min Act: -0.1700
Data Index: 7053343 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2154. Min Range: -5.2154
Max Act: 5.0279. Min Act: -0.1700
Data Index: 2605403 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2154. Min Range: -5.2154
Max Act: 5.0592. Min Act: -0.1700
Data Index: 4796649 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2154. Min Range: -5.2154
Max Act: 4.9967. Min Act: -0.1700
Data Index: 8290677 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2154. Min Range: -5.2154
Max Act: 4.9967. Min Act: -0.1700
Data Index: 4230819 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2154. Min Range: -5.2154
Max Act: 4.9654. Min Act: -0.1700
Data Index: 5315619 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2154. Min Range: -5.2154
Max Act: 4.9654. Min Act: -0.1700
Data Index: 4874540 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2154. Min Range: -5.2154
Max Act: 4.9654. Min Act: -0.1700
Data Index: 1180130 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2154. Min Range: -5.2154
Max Act: 4.9654. Min Act: -0.1700
Data Index: 8617313 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2154. Min Range: -5.2154
Max Act: 4.9654. Min Act: -0.1700
Data Index: 1965980 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2154. Min Range: -5.2154
Max Act: 4.9342. Min Act: -0.1700
Data Index: 4318562 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2154. Min Range: -5.2154
Max Act: 4.9342. Min Act: -0.1700
Data Index: 585791 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #19