Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2097 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2725. Min Range: -7.2725
Max Act: 7.2725. Min Act: -0.1700
Data Index: 7623487 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2725. Min Range: -7.2725
Max Act: 7.1475. Min Act: -0.1700
Data Index: 8505528 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2725. Min Range: -7.2725
Max Act: 7.1475. Min Act: -0.1700
Data Index: 6817954 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2725. Min Range: -7.2725
Max Act: 7.1475. Min Act: -0.1700
Data Index: 1369471 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2725. Min Range: -7.2725
Max Act: 7.1163. Min Act: -0.1700
Data Index: 6346554 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2725. Min Range: -7.2725
Max Act: 7.1163. Min Act: -0.1700
Data Index: 1092265 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2725. Min Range: -7.2725
Max Act: 7.0850. Min Act: -0.1700
Data Index: 4361840 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2725. Min Range: -7.2725
Max Act: 7.0225. Min Act: -0.1700
Data Index: 7626845 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2725. Min Range: -7.2725
Max Act: 6.9913. Min Act: -0.1700
Data Index: 5214873 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2725. Min Range: -7.2725
Max Act: 6.9913. Min Act: -0.1700
Data Index: 1561876 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2725. Min Range: -7.2725
Max Act: 6.9600. Min Act: -0.1700
Data Index: 5396895 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2725. Min Range: -7.2725
Max Act: 6.9288. Min Act: -0.1700
Data Index: 5097624 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2725. Min Range: -7.2725
Max Act: 6.8975. Min Act: -0.1700
Data Index: 6189052 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2725. Min Range: -7.2725
Max Act: 6.8975. Min Act: -0.1700
Data Index: 2095059 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2725. Min Range: -7.2725
Max Act: 6.8663. Min Act: -0.1700
Data Index: 560210 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2725. Min Range: -7.2725
Max Act: 6.8350. Min Act: -0.1700
Data Index: 2279008 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2725. Min Range: -7.2725
Max Act: 6.8350. Min Act: -0.1700
Data Index: 1461140 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2725. Min Range: -7.2725
Max Act: 6.8350. Min Act: -0.1700
Data Index: 2608824 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2725. Min Range: -7.2725
Max Act: 6.7725. Min Act: -0.1700
Data Index: 5741341 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2725. Min Range: -7.2725
Max Act: 6.7725. Min Act: -0.1700
Data Index: 5769892 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #19