Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1506 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6508. Min Range: -5.6508
Max Act: 5.6508. Min Act: -0.1700
Data Index: 980893 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6508. Min Range: -5.6508
Max Act: 5.5570. Min Act: -0.1700
Data Index: 26189 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6508. Min Range: -5.6508
Max Act: 5.4320. Min Act: -0.1700
Data Index: 1827139 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6508. Min Range: -5.6508
Max Act: 5.3383. Min Act: -0.1700
Data Index: 5009625 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6508. Min Range: -5.6508
Max Act: 5.3383. Min Act: -0.1700
Data Index: 1693019 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6508. Min Range: -5.6508
Max Act: 5.3695. Min Act: -0.1700
Data Index: 3380464 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6508. Min Range: -5.6508
Max Act: 5.3383. Min Act: -0.1700
Data Index: 1788320 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6508. Min Range: -5.6508
Max Act: 5.3383. Min Act: -0.1700
Data Index: 6032430 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6508. Min Range: -5.6508
Max Act: 5.3070. Min Act: -0.1700
Data Index: 1205849 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6508. Min Range: -5.6508
Max Act: 5.3070. Min Act: -0.1700
Data Index: 1589080 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6508. Min Range: -5.6508
Max Act: 5.3070. Min Act: -0.1700
Data Index: 3753350 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6508. Min Range: -5.6508
Max Act: 5.3070. Min Act: -0.1700
Data Index: 7681770 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6508. Min Range: -5.6508
Max Act: 5.2758. Min Act: -0.1700
Data Index: 4554969 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6508. Min Range: -5.6508
Max Act: 5.2758. Min Act: -0.1700
Data Index: 1160771 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6508. Min Range: -5.6508
Max Act: 5.2758. Min Act: -0.1700
Data Index: 3179031 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6508. Min Range: -5.6508
Max Act: 5.2445. Min Act: -0.1700
Data Index: 1156015 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6508. Min Range: -5.6508
Max Act: 5.2445. Min Act: -0.1700
Data Index: 2199076 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6508. Min Range: -5.6508
Max Act: 5.2445. Min Act: -0.1700
Data Index: 2187007 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6508. Min Range: -5.6508
Max Act: 5.2758. Min Act: -0.1700
Data Index: 1043980 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6508. Min Range: -5.6508
Max Act: 5.2133. Min Act: -0.1700
Data Index: 7176386 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #19