Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5211 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4511. Min Range: -6.4511
Max Act: 6.4511. Min Act: -0.1700
Data Index: 3150347 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4511. Min Range: -6.4511
Max Act: 6.3261. Min Act: -0.1700
Data Index: 2972542 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4511. Min Range: -6.4511
Max Act: 6.2323. Min Act: -0.1700
Data Index: 8091626 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4511. Min Range: -6.4511
Max Act: 6.1698. Min Act: -0.1700
Data Index: 340886 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4511. Min Range: -6.4511
Max Act: 6.1698. Min Act: -0.1700
Data Index: 929190 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4511. Min Range: -6.4511
Max Act: 6.2011. Min Act: -0.1700
Data Index: 2201724 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4511. Min Range: -6.4511
Max Act: 6.1386. Min Act: -0.1700
Data Index: 5051694 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4511. Min Range: -6.4511
Max Act: 6.1386. Min Act: -0.1700
Data Index: 423869 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4511. Min Range: -6.4511
Max Act: 6.0136. Min Act: -0.1700
Data Index: 3185291 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4511. Min Range: -6.4511
Max Act: 5.9823. Min Act: -0.1700
Data Index: 8302119 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4511. Min Range: -6.4511
Max Act: 5.9198. Min Act: -0.1700
Data Index: 1136591 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4511. Min Range: -6.4511
Max Act: 5.9198. Min Act: -0.1700
Data Index: 1961120 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4511. Min Range: -6.4511
Max Act: 5.9511. Min Act: -0.1700
Data Index: 6968911 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4511. Min Range: -6.4511
Max Act: 5.9198. Min Act: -0.1700
Data Index: 5060390 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4511. Min Range: -6.4511
Max Act: 5.8886. Min Act: -0.1700
Data Index: 5510072 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4511. Min Range: -6.4511
Max Act: 5.8886. Min Act: -0.1700
Data Index: 1894546 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4511. Min Range: -6.4511
Max Act: 5.8886. Min Act: -0.1700
Data Index: 1230689 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4511. Min Range: -6.4511
Max Act: 5.8886. Min Act: -0.1700
Data Index: 5532956 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4511. Min Range: -6.4511
Max Act: 5.9198. Min Act: -0.1700
Data Index: 4108707 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4511. Min Range: -6.4511
Max Act: 5.8886. Min Act: -0.1700
Data Index: 4513432 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #19