Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6350 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5695. Min Range: -5.5695
Max Act: 5.5695. Min Act: -0.1700
Data Index: 7384510 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5695. Min Range: -5.5695
Max Act: 5.5070. Min Act: -0.1700
Data Index: 1265465 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5695. Min Range: -5.5695
Max Act: 5.3508. Min Act: -0.1700
Data Index: 7995092 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5695. Min Range: -5.5695
Max Act: 5.3508. Min Act: -0.1700
Data Index: 5240632 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5695. Min Range: -5.5695
Max Act: 5.2570. Min Act: -0.1700
Data Index: 5883546 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5695. Min Range: -5.5695
Max Act: 5.1633. Min Act: -0.1700
Data Index: 8563044 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5695. Min Range: -5.5695
Max Act: 5.1633. Min Act: -0.1700
Data Index: 7840503 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5695. Min Range: -5.5695
Max Act: 5.1633. Min Act: -0.1700
Data Index: 2233733 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5695. Min Range: -5.5695
Max Act: 5.1320. Min Act: -0.1700
Data Index: 5706312 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5695. Min Range: -5.5695
Max Act: 5.1320. Min Act: -0.1700
Data Index: 1172623 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5695. Min Range: -5.5695
Max Act: 5.1633. Min Act: -0.1700
Data Index: 3695919 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5695. Min Range: -5.5695
Max Act: 5.1633. Min Act: -0.1700
Data Index: 2260861 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5695. Min Range: -5.5695
Max Act: 5.1008. Min Act: -0.1700
Data Index: 2635877 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5695. Min Range: -5.5695
Max Act: 5.1008. Min Act: -0.1700
Data Index: 1108909 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5695. Min Range: -5.5695
Max Act: 5.1008. Min Act: -0.1700
Data Index: 5651284 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5695. Min Range: -5.5695
Max Act: 5.1008. Min Act: -0.1700
Data Index: 2349288 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5695. Min Range: -5.5695
Max Act: 5.1008. Min Act: -0.1700
Data Index: 8593057 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5695. Min Range: -5.5695
Max Act: 5.0383. Min Act: -0.1700
Data Index: 7149274 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5695. Min Range: -5.5695
Max Act: 5.0695. Min Act: -0.1700
Data Index: 6706626 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5695. Min Range: -5.5695
Max Act: 5.0695. Min Act: -0.1700
Data Index: 2321348 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #19