Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4716 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6528. Min Range: -7.6528
Max Act: 7.6528. Min Act: -0.1700
Data Index: 4027309 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6528. Min Range: -7.6528
Max Act: 7.4340. Min Act: -0.1700
Data Index: 5566284 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6528. Min Range: -7.6528
Max Act: 7.4340. Min Act: -0.1700
Data Index: 7597988 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6528. Min Range: -7.6528
Max Act: 7.4028. Min Act: -0.1700
Data Index: 2716258 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6528. Min Range: -7.6528
Max Act: 7.3403. Min Act: -0.1700
Data Index: 940827 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6528. Min Range: -7.6528
Max Act: 7.3403. Min Act: -0.1700
Data Index: 54555 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6528. Min Range: -7.6528
Max Act: 7.3090. Min Act: -0.1700
Data Index: 209890 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6528. Min Range: -7.6528
Max Act: 7.3090. Min Act: -0.1700
Data Index: 8167452 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6528. Min Range: -7.6528
Max Act: 7.2465. Min Act: -0.1700
Data Index: 6523483 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6528. Min Range: -7.6528
Max Act: 7.2465. Min Act: -0.1700
Data Index: 2322306 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6528. Min Range: -7.6528
Max Act: 7.1840. Min Act: -0.1700
Data Index: 6776470 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6528. Min Range: -7.6528
Max Act: 7.1840. Min Act: -0.1700
Data Index: 4383663 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6528. Min Range: -7.6528
Max Act: 7.1840. Min Act: -0.1700
Data Index: 7568177 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6528. Min Range: -7.6528
Max Act: 7.1528. Min Act: -0.1700
Data Index: 2247711 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6528. Min Range: -7.6528
Max Act: 7.1528. Min Act: -0.1700
Data Index: 2165957 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6528. Min Range: -7.6528
Max Act: 7.1840. Min Act: -0.1700
Data Index: 4268585 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6528. Min Range: -7.6528
Max Act: 7.1528. Min Act: -0.1700
Data Index: 201430 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6528. Min Range: -7.6528
Max Act: 7.1215. Min Act: -0.1700
Data Index: 3171003 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6528. Min Range: -7.6528
Max Act: 7.1215. Min Act: -0.1700
Data Index: 8167453 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6528. Min Range: -7.6528
Max Act: 7.1215. Min Act: -0.1700
Data Index: 645117 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #19