Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 955 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6300. Min Range: -4.6300
Max Act: 4.6300. Min Act: -0.1700
Data Index: 2672314 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6300. Min Range: -4.6300
Max Act: 4.5675. Min Act: -0.1700
Data Index: 703295 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6300. Min Range: -4.6300
Max Act: 4.5363. Min Act: -0.1700
Data Index: 5851046 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6300. Min Range: -4.6300
Max Act: 4.5363. Min Act: -0.1700
Data Index: 2643854 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6300. Min Range: -4.6300
Max Act: 4.4113. Min Act: -0.1700
Data Index: 6553200 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6300. Min Range: -4.6300
Max Act: 4.4113. Min Act: -0.1700
Data Index: 2554528 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6300. Min Range: -4.6300
Max Act: 4.3800. Min Act: -0.1700
Data Index: 6101544 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6300. Min Range: -4.6300
Max Act: 4.3800. Min Act: -0.1700
Data Index: 1453354 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6300. Min Range: -4.6300
Max Act: 4.3800. Min Act: -0.1700
Data Index: 8258802 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6300. Min Range: -4.6300
Max Act: 4.3800. Min Act: -0.1700
Data Index: 258536 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6300. Min Range: -4.6300
Max Act: 4.3175. Min Act: -0.1700
Data Index: 45099 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6300. Min Range: -4.6300
Max Act: 4.3488. Min Act: -0.1700
Data Index: 4556994 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6300. Min Range: -4.6300
Max Act: 4.3488. Min Act: -0.1700
Data Index: 1027595 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6300. Min Range: -4.6300
Max Act: 4.3488. Min Act: -0.1700
Data Index: 3160081 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6300. Min Range: -4.6300
Max Act: 4.3488. Min Act: -0.1700
Data Index: 1391635 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6300. Min Range: -4.6300
Max Act: 4.2863. Min Act: -0.1700
Data Index: 2967121 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6300. Min Range: -4.6300
Max Act: 4.3175. Min Act: -0.1700
Data Index: 8295968 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6300. Min Range: -4.6300
Max Act: 4.3175. Min Act: -0.1700
Data Index: 7272476 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6300. Min Range: -4.6300
Max Act: 4.3175. Min Act: -0.1700
Data Index: 1705599 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6300. Min Range: -4.6300
Max Act: 4.3175. Min Act: -0.1700
Data Index: 8258799 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #19