Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4656 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6484. Min Range: -5.6484
Max Act: 5.6484. Min Act: -0.1700
Data Index: 5841484 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6484. Min Range: -5.6484
Max Act: 5.4922. Min Act: -0.1700
Data Index: 2757198 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6484. Min Range: -5.6484
Max Act: 5.4609. Min Act: -0.1700
Data Index: 57145 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6484. Min Range: -5.6484
Max Act: 5.4297. Min Act: -0.1700
Data Index: 7419026 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6484. Min Range: -5.6484
Max Act: 5.3984. Min Act: -0.1700
Data Index: 3169998 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6484. Min Range: -5.6484
Max Act: 5.3359. Min Act: -0.1700
Data Index: 6014570 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6484. Min Range: -5.6484
Max Act: 5.3047. Min Act: -0.1700
Data Index: 1896069 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6484. Min Range: -5.6484
Max Act: 5.2734. Min Act: -0.1700
Data Index: 1119344 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6484. Min Range: -5.6484
Max Act: 5.2734. Min Act: -0.1700
Data Index: 3612477 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6484. Min Range: -5.6484
Max Act: 5.2422. Min Act: -0.1700
Data Index: 1607051 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6484. Min Range: -5.6484
Max Act: 5.1797. Min Act: -0.1700
Data Index: 5760096 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6484. Min Range: -5.6484
Max Act: 5.2109. Min Act: -0.1700
Data Index: 6424219 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6484. Min Range: -5.6484
Max Act: 5.1797. Min Act: -0.1700
Data Index: 527325 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6484. Min Range: -5.6484
Max Act: 5.2109. Min Act: -0.1699
Data Index: 6264956 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6484. Min Range: -5.6484
Max Act: 5.1484. Min Act: -0.1700
Data Index: 6217264 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6484. Min Range: -5.6484
Max Act: 5.1484. Min Act: -0.1700
Data Index: 3094363 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6484. Min Range: -5.6484
Max Act: 5.1484. Min Act: -0.1700
Data Index: 201526 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6484. Min Range: -5.6484
Max Act: 5.1484. Min Act: -0.1700
Data Index: 4184286 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6484. Min Range: -5.6484
Max Act: 5.1484. Min Act: -0.1700
Data Index: 4799727 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6484. Min Range: -5.6484
Max Act: 5.1172. Min Act: -0.1700
Data Index: 1122991 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #19