Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2319 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3661. Min Range: -7.3661
Max Act: 7.3661. Min Act: -0.1700
Data Index: 3737739 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3661. Min Range: -7.3661
Max Act: 7.2724. Min Act: -0.1700
Data Index: 6522847 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3661. Min Range: -7.3661
Max Act: 7.1474. Min Act: -0.1700
Data Index: 7881238 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3661. Min Range: -7.3661
Max Act: 7.0224. Min Act: -0.1700
Data Index: 3485476 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3661. Min Range: -7.3661
Max Act: 7.0224. Min Act: -0.1700
Data Index: 5489600 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3661. Min Range: -7.3661
Max Act: 6.9911. Min Act: -0.1700
Data Index: 428708 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3661. Min Range: -7.3661
Max Act: 6.9599. Min Act: -0.1700
Data Index: 7123789 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3661. Min Range: -7.3661
Max Act: 6.9286. Min Act: -0.1700
Data Index: 422493 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3661. Min Range: -7.3661
Max Act: 6.8974. Min Act: -0.1700
Data Index: 6152680 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3661. Min Range: -7.3661
Max Act: 6.9286. Min Act: -0.1700
Data Index: 1708860 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3661. Min Range: -7.3661
Max Act: 6.8974. Min Act: -0.1700
Data Index: 3212171 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3661. Min Range: -7.3661
Max Act: 6.8661. Min Act: -0.1700
Data Index: 1095717 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3661. Min Range: -7.3661
Max Act: 6.8349. Min Act: -0.1700
Data Index: 2635613 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3661. Min Range: -7.3661
Max Act: 6.8036. Min Act: -0.1700
Data Index: 6203520 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3661. Min Range: -7.3661
Max Act: 6.8349. Min Act: -0.1700
Data Index: 6064354 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3661. Min Range: -7.3661
Max Act: 6.8036. Min Act: -0.1700
Data Index: 7260759 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3661. Min Range: -7.3661
Max Act: 6.7724. Min Act: -0.1700
Data Index: 374288 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3661. Min Range: -7.3661
Max Act: 6.7724. Min Act: -0.1700
Data Index: 3693882 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3661. Min Range: -7.3661
Max Act: 6.7724. Min Act: -0.1700
Data Index: 1549176 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3661. Min Range: -7.3661
Max Act: 6.7724. Min Act: -0.1700
Data Index: 1471154 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #19