Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 574 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6484. Min Range: -4.6484
Max Act: 4.6484. Min Act: -0.1700
Data Index: 2566202 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6484. Min Range: -4.6484
Max Act: 4.6172. Min Act: -0.1700
Data Index: 8628938 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6484. Min Range: -4.6484
Max Act: 4.5859. Min Act: -0.1700
Data Index: 3062101 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6484. Min Range: -4.6484
Max Act: 4.4922. Min Act: -0.1700
Data Index: 4107628 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6484. Min Range: -4.6484
Max Act: 4.4609. Min Act: -0.1700
Data Index: 7093721 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6484. Min Range: -4.6484
Max Act: 4.4609. Min Act: -0.1700
Data Index: 7818021 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6484. Min Range: -4.6484
Max Act: 4.4609. Min Act: -0.1700
Data Index: 5668880 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6484. Min Range: -4.6484
Max Act: 4.3984. Min Act: -0.1700
Data Index: 6808683 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6484. Min Range: -4.6484
Max Act: 4.3672. Min Act: -0.1700
Data Index: 2833091 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6484. Min Range: -4.6484
Max Act: 4.3984. Min Act: -0.1700
Data Index: 3414546 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6484. Min Range: -4.6484
Max Act: 4.3359. Min Act: -0.1700
Data Index: 3820750 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6484. Min Range: -4.6484
Max Act: 4.3359. Min Act: -0.1700
Data Index: 5755326 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6484. Min Range: -4.6484
Max Act: 4.3359. Min Act: -0.1700
Data Index: 6678691 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6484. Min Range: -4.6484
Max Act: 4.3359. Min Act: -0.1700
Data Index: 8517991 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6484. Min Range: -4.6484
Max Act: 4.3359. Min Act: -0.1700
Data Index: 5346407 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6484. Min Range: -4.6484
Max Act: 4.3047. Min Act: -0.1700
Data Index: 433004 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6484. Min Range: -4.6484
Max Act: 4.3047. Min Act: -0.1700
Data Index: 6052320 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6484. Min Range: -4.6484
Max Act: 4.3047. Min Act: -0.1700
Data Index: 5949833 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6484. Min Range: -4.6484
Max Act: 4.3047. Min Act: -0.1700
Data Index: 4825999 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6484. Min Range: -4.6484
Max Act: 4.2734. Min Act: -0.1700
Data Index: 1470025 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #19