Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5135 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8905. Min Range: -5.8905
Max Act: 5.8905. Min Act: -0.1700
Data Index: 1175351 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8905. Min Range: -5.8905
Max Act: 5.6092. Min Act: -0.1700
Data Index: 4094123 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8905. Min Range: -5.8905
Max Act: 5.5780. Min Act: -0.1700
Data Index: 8139484 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8905. Min Range: -5.8905
Max Act: 5.5467. Min Act: -0.1700
Data Index: 1450948 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8905. Min Range: -5.8905
Max Act: 5.3280. Min Act: -0.1700
Data Index: 560073 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8905. Min Range: -5.8905
Max Act: 5.3280. Min Act: -0.1700
Data Index: 2147210 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8905. Min Range: -5.8905
Max Act: 5.3280. Min Act: -0.1700
Data Index: 2880143 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8905. Min Range: -5.8905
Max Act: 5.1717. Min Act: -0.1700
Data Index: 1819959 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8905. Min Range: -5.8905
Max Act: 5.1717. Min Act: -0.1700
Data Index: 7395817 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8905. Min Range: -5.8905
Max Act: 5.2030. Min Act: -0.1700
Data Index: 4904482 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8905. Min Range: -5.8905
Max Act: 5.1717. Min Act: -0.1700
Data Index: 1063416 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8905. Min Range: -5.8905
Max Act: 5.2030. Min Act: -0.1700
Data Index: 7395377 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8905. Min Range: -5.8905
Max Act: 5.1717. Min Act: -0.1700
Data Index: 4852396 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8905. Min Range: -5.8905
Max Act: 5.1405. Min Act: -0.1700
Data Index: 7170982 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8905. Min Range: -5.8905
Max Act: 5.1405. Min Act: -0.1700
Data Index: 959882 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8905. Min Range: -5.8905
Max Act: 5.1092. Min Act: -0.1700
Data Index: 525949 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8905. Min Range: -5.8905
Max Act: 5.1092. Min Act: -0.1700
Data Index: 926294 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8905. Min Range: -5.8905
Max Act: 5.1092. Min Act: -0.1700
Data Index: 4364293 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8905. Min Range: -5.8905
Max Act: 5.1092. Min Act: -0.1700
Data Index: 7086250 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8905. Min Range: -5.8905
Max Act: 5.1092. Min Act: -0.1700
Data Index: 430636 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #19