Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1159 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.6576. Min Range: -9.6576
Max Act: 9.6576. Min Act: -0.1700
Data Index: 4267600 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.6576. Min Range: -9.6576
Max Act: 9.4701. Min Act: -0.1700
Data Index: 383593 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.6576. Min Range: -9.6576
Max Act: 9.4701. Min Act: -0.1700
Data Index: 4713168 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.6576. Min Range: -9.6576
Max Act: 9.4076. Min Act: -0.1700
Data Index: 199891 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.6576. Min Range: -9.6576
Max Act: 9.4076. Min Act: -0.1700
Data Index: 7593823 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.6576. Min Range: -9.6576
Max Act: 9.4076. Min Act: -0.1700
Data Index: 3811879 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.6576. Min Range: -9.6576
Max Act: 9.3451. Min Act: -0.1700
Data Index: 4740829 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.6576. Min Range: -9.6576
Max Act: 9.3451. Min Act: -0.1700
Data Index: 3183012 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.6576. Min Range: -9.6576
Max Act: 9.2826. Min Act: -0.1700
Data Index: 8701281 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.6576. Min Range: -9.6576
Max Act: 9.2826. Min Act: -0.1700
Data Index: 5848442 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.6576. Min Range: -9.6576
Max Act: 9.3451. Min Act: -0.1700
Data Index: 5822203 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.6576. Min Range: -9.6576
Max Act: 9.2826. Min Act: -0.1700
Data Index: 8393269 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.6576. Min Range: -9.6576
Max Act: 9.2201. Min Act: -0.1700
Data Index: 1237519 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.6576. Min Range: -9.6576
Max Act: 9.2201. Min Act: -0.1700
Data Index: 2633701 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.6576. Min Range: -9.6576
Max Act: 9.2201. Min Act: -0.1700
Data Index: 3173838 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.6576. Min Range: -9.6576
Max Act: 9.2201. Min Act: -0.1700
Data Index: 1849979 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.6576. Min Range: -9.6576
Max Act: 9.1576. Min Act: -0.1700
Data Index: 7246771 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.6576. Min Range: -9.6576
Max Act: 9.0951. Min Act: -0.1700
Data Index: 2496909 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.6576. Min Range: -9.6576
Max Act: 9.0951. Min Act: -0.1700
Data Index: 827057 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.6576. Min Range: -9.6576
Max Act: 9.0951. Min Act: -0.1700
Data Index: 4040017 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #19