Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3816 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9105. Min Range: -6.9105
Max Act: 6.9105. Min Act: -0.1694
Data Index: 2506113 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9105. Min Range: -6.9105
Max Act: 6.9105. Min Act: -0.1700
Data Index: 3121874 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9105. Min Range: -6.9105
Max Act: 6.5980. Min Act: -0.1700
Data Index: 3901373 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9105. Min Range: -6.9105
Max Act: 6.5980. Min Act: -0.1700
Data Index: 2513526 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9105. Min Range: -6.9105
Max Act: 6.5668. Min Act: -0.1700
Data Index: 5142046 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9105. Min Range: -6.9105
Max Act: 6.4418. Min Act: -0.1700
Data Index: 686002 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9105. Min Range: -6.9105
Max Act: 6.4730. Min Act: -0.1700
Data Index: 774749 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9105. Min Range: -6.9105
Max Act: 6.4418. Min Act: -0.1700
Data Index: 5903832 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9105. Min Range: -6.9105
Max Act: 6.3793. Min Act: -0.1700
Data Index: 3744921 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9105. Min Range: -6.9105
Max Act: 6.4105. Min Act: -0.1700
Data Index: 5990016 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9105. Min Range: -6.9105
Max Act: 6.3480. Min Act: -0.1700
Data Index: 375277 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9105. Min Range: -6.9105
Max Act: 6.3480. Min Act: -0.1700
Data Index: 3547174 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9105. Min Range: -6.9105
Max Act: 6.2855. Min Act: -0.1700
Data Index: 8366287 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9105. Min Range: -6.9105
Max Act: 6.2543. Min Act: -0.1700
Data Index: 4213540 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9105. Min Range: -6.9105
Max Act: 6.2543. Min Act: -0.1700
Data Index: 3913096 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9105. Min Range: -6.9105
Max Act: 6.2230. Min Act: -0.1700
Data Index: 805738 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9105. Min Range: -6.9105
Max Act: 6.1918. Min Act: -0.1700
Data Index: 5074469 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9105. Min Range: -6.9105
Max Act: 6.1605. Min Act: -0.1700
Data Index: 632740 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9105. Min Range: -6.9105
Max Act: 6.1605. Min Act: -0.1700
Data Index: 5100327 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9105. Min Range: -6.9105
Max Act: 6.1605. Min Act: -0.1700
Data Index: 5103392 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #19