Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2870 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9279. Min Range: -5.9279
Max Act: 5.9279. Min Act: -0.1700
Data Index: 8108772 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9279. Min Range: -5.9279
Max Act: 5.8654. Min Act: -0.1700
Data Index: 1750126 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9279. Min Range: -5.9279
Max Act: 5.8654. Min Act: -0.1700
Data Index: 6819900 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9279. Min Range: -5.9279
Max Act: 5.8654. Min Act: -0.1700
Data Index: 5668704 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9279. Min Range: -5.9279
Max Act: 5.8654. Min Act: -0.1700
Data Index: 8287883 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9279. Min Range: -5.9279
Max Act: 5.8342. Min Act: -0.1700
Data Index: 5342720 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9279. Min Range: -5.9279
Max Act: 5.8342. Min Act: -0.1700
Data Index: 7676122 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9279. Min Range: -5.9279
Max Act: 5.8029. Min Act: -0.1700
Data Index: 5583500 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9279. Min Range: -5.9279
Max Act: 5.8029. Min Act: -0.1700
Data Index: 4510570 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9279. Min Range: -5.9279
Max Act: 5.7717. Min Act: -0.1700
Data Index: 4070735 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9279. Min Range: -5.9279
Max Act: 5.7404. Min Act: -0.1700
Data Index: 4074562 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9279. Min Range: -5.9279
Max Act: 5.7404. Min Act: -0.1700
Data Index: 5331635 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9279. Min Range: -5.9279
Max Act: 5.7404. Min Act: -0.1700
Data Index: 2800535 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9279. Min Range: -5.9279
Max Act: 5.7404. Min Act: -0.1700
Data Index: 2912883 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9279. Min Range: -5.9279
Max Act: 5.7717. Min Act: -0.1700
Data Index: 739260 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9279. Min Range: -5.9279
Max Act: 5.7404. Min Act: -0.1700
Data Index: 4301433 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9279. Min Range: -5.9279
Max Act: 5.7092. Min Act: -0.1700
Data Index: 5684516 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9279. Min Range: -5.9279
Max Act: 5.7092. Min Act: -0.1700
Data Index: 1505300 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9279. Min Range: -5.9279
Max Act: 5.7092. Min Act: -0.1700
Data Index: 4751478 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9279. Min Range: -5.9279
Max Act: 5.6779. Min Act: -0.1700
Data Index: 635156 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #19