Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5883 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5301. Min Range: -6.5301
Max Act: 6.5301. Min Act: -0.1700
Data Index: 3487437 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5301. Min Range: -6.5301
Max Act: 6.4051. Min Act: -0.1700
Data Index: 1698827 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5301. Min Range: -6.5301
Max Act: 6.3739. Min Act: -0.1700
Data Index: 68694 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5301. Min Range: -6.5301
Max Act: 6.3739. Min Act: -0.1700
Data Index: 3523632 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5301. Min Range: -6.5301
Max Act: 6.3739. Min Act: -0.1700
Data Index: 4580097 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5301. Min Range: -6.5301
Max Act: 6.3426. Min Act: -0.1700
Data Index: 6357006 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5301. Min Range: -6.5301
Max Act: 6.3114. Min Act: -0.1700
Data Index: 1326433 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5301. Min Range: -6.5301
Max Act: 6.2801. Min Act: -0.1700
Data Index: 7015513 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5301. Min Range: -6.5301
Max Act: 6.2801. Min Act: -0.1700
Data Index: 7315922 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5301. Min Range: -6.5301
Max Act: 6.2801. Min Act: -0.1700
Data Index: 3529809 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5301. Min Range: -6.5301
Max Act: 6.2801. Min Act: -0.1700
Data Index: 3741933 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5301. Min Range: -6.5301
Max Act: 6.2801. Min Act: -0.1700
Data Index: 2319632 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5301. Min Range: -6.5301
Max Act: 6.2489. Min Act: -0.1700
Data Index: 2133923 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5301. Min Range: -6.5301
Max Act: 6.2489. Min Act: -0.1700
Data Index: 7077311 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5301. Min Range: -6.5301
Max Act: 6.2489. Min Act: -0.1700
Data Index: 5125860 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5301. Min Range: -6.5301
Max Act: 6.2176. Min Act: -0.1700
Data Index: 4469640 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5301. Min Range: -6.5301
Max Act: 6.2176. Min Act: -0.1700
Data Index: 5450328 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5301. Min Range: -6.5301
Max Act: 6.2176. Min Act: -0.1700
Data Index: 5479315 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5301. Min Range: -6.5301
Max Act: 6.2176. Min Act: -0.1700
Data Index: 5226646 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5301. Min Range: -6.5301
Max Act: 6.2176. Min Act: -0.1700
Data Index: 6667176 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #19