Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3132 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8015. Min Range: -5.8015
Max Act: 5.8015. Min Act: -0.1700
Data Index: 1383185 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8015. Min Range: -5.8015
Max Act: 5.7702. Min Act: -0.1700
Data Index: 3520701 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8015. Min Range: -5.8015
Max Act: 5.6140. Min Act: -0.1700
Data Index: 6364278 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8015. Min Range: -5.8015
Max Act: 5.5515. Min Act: -0.1700
Data Index: 5768211 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8015. Min Range: -5.8015
Max Act: 5.5515. Min Act: -0.1700
Data Index: 6905232 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8015. Min Range: -5.8015
Max Act: 5.5515. Min Act: -0.1700
Data Index: 7072430 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8015. Min Range: -5.8015
Max Act: 5.5202. Min Act: -0.1700
Data Index: 8365873 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8015. Min Range: -5.8015
Max Act: 5.5202. Min Act: -0.1700
Data Index: 508946 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8015. Min Range: -5.8015
Max Act: 5.4890. Min Act: -0.1700
Data Index: 3894888 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8015. Min Range: -5.8015
Max Act: 5.4890. Min Act: -0.1700
Data Index: 5159015 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8015. Min Range: -5.8015
Max Act: 5.4890. Min Act: -0.1700
Data Index: 8792788 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8015. Min Range: -5.8015
Max Act: 5.4890. Min Act: -0.1700
Data Index: 1955598 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8015. Min Range: -5.8015
Max Act: 5.4577. Min Act: -0.1700
Data Index: 5685663 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8015. Min Range: -5.8015
Max Act: 5.4577. Min Act: -0.1700
Data Index: 4580047 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8015. Min Range: -5.8015
Max Act: 5.4577. Min Act: -0.1700
Data Index: 297648 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8015. Min Range: -5.8015
Max Act: 5.4265. Min Act: -0.1700
Data Index: 7316734 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8015. Min Range: -5.8015
Max Act: 5.4577. Min Act: -0.1700
Data Index: 8735844 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8015. Min Range: -5.8015
Max Act: 5.4265. Min Act: -0.1700
Data Index: 7072431 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8015. Min Range: -5.8015
Max Act: 5.4265. Min Act: -0.1700
Data Index: 3894881 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8015. Min Range: -5.8015
Max Act: 5.4265. Min Act: -0.1700
Data Index: 353884 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #19