Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1517 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.6646. Min Range: -4.6646
Max Act: 4.6646. Min Act: -0.1700
Data Index: 1376349 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6646. Min Range: -4.6646
Max Act: 4.4771. Min Act: -0.1700
Data Index: 3166385 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6646. Min Range: -4.6646
Max Act: 4.4458. Min Act: -0.1700
Data Index: 6854214 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6646. Min Range: -4.6646
Max Act: 4.4458. Min Act: -0.1700
Data Index: 2145529 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6646. Min Range: -4.6646
Max Act: 4.4771. Min Act: -0.1700
Data Index: 911167 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6646. Min Range: -4.6646
Max Act: 4.4458. Min Act: -0.1700
Data Index: 699329 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6646. Min Range: -4.6646
Max Act: 4.4146. Min Act: -0.1700
Data Index: 6913925 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6646. Min Range: -4.6646
Max Act: 4.3833. Min Act: -0.1700
Data Index: 4358200 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6646. Min Range: -4.6646
Max Act: 4.4458. Min Act: -0.1700
Data Index: 6131910 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6646. Min Range: -4.6646
Max Act: 4.4146. Min Act: -0.1700
Data Index: 5594114 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6646. Min Range: -4.6646
Max Act: 4.3833. Min Act: -0.1700
Data Index: 3406938 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6646. Min Range: -4.6646
Max Act: 4.3833. Min Act: -0.1700
Data Index: 1997606 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6646. Min Range: -4.6646
Max Act: 4.4146. Min Act: -0.1700
Data Index: 795104 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6646. Min Range: -4.6646
Max Act: 4.3520. Min Act: -0.1700
Data Index: 2473165 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6646. Min Range: -4.6646
Max Act: 4.3520. Min Act: -0.1700
Data Index: 5313675 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6646. Min Range: -4.6646
Max Act: 4.3520. Min Act: -0.1700
Data Index: 4580081 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6646. Min Range: -4.6646
Max Act: 4.3520. Min Act: -0.1700
Data Index: 965188 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6646. Min Range: -4.6646
Max Act: 4.3520. Min Act: -0.1700
Data Index: 3215905 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6646. Min Range: -4.6646
Max Act: 4.3520. Min Act: -0.1700
Data Index: 454242 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6646. Min Range: -4.6646
Max Act: 4.3520. Min Act: -0.1700
Data Index: 2901810 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #19