Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2395 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.7614. Min Range: -3.7614
Max Act: 3.7614. Min Act: -0.1700
Data Index: 4316859 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7614. Min Range: -3.7614
Max Act: 3.7301. Min Act: -0.1700
Data Index: 533602 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7614. Min Range: -3.7614
Max Act: 3.7301. Min Act: -0.1700
Data Index: 7374997 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7614. Min Range: -3.7614
Max Act: 3.6988. Min Act: -0.1700
Data Index: 4316858 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7614. Min Range: -3.7614
Max Act: 3.6988. Min Act: -0.1700
Data Index: 902307 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7614. Min Range: -3.7614
Max Act: 3.6988. Min Act: -0.1700
Data Index: 6096249 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7614. Min Range: -3.7614
Max Act: 3.6988. Min Act: -0.1700
Data Index: 4485892 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7614. Min Range: -3.7614
Max Act: 3.6675. Min Act: -0.1700
Data Index: 3390258 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7614. Min Range: -3.7614
Max Act: 3.6675. Min Act: -0.1700
Data Index: 4637176 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7614. Min Range: -3.7614
Max Act: 3.6675. Min Act: -0.1700
Data Index: 2440538 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7614. Min Range: -3.7614
Max Act: 3.6363. Min Act: -0.1700
Data Index: 6139143 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7614. Min Range: -3.7614
Max Act: 3.6050. Min Act: -0.1700
Data Index: 5221719 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7614. Min Range: -3.7614
Max Act: 3.6050. Min Act: -0.1700
Data Index: 6454572 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7614. Min Range: -3.7614
Max Act: 3.6050. Min Act: -0.1700
Data Index: 3513536 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7614. Min Range: -3.7614
Max Act: 3.5736. Min Act: -0.1700
Data Index: 2069604 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7614. Min Range: -3.7614
Max Act: 3.5736. Min Act: -0.1700
Data Index: 5391260 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7614. Min Range: -3.7614
Max Act: 3.5736. Min Act: -0.1700
Data Index: 545364 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7614. Min Range: -3.7614
Max Act: 3.5736. Min Act: -0.1700
Data Index: 5056542 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7614. Min Range: -3.7614
Max Act: 3.5736. Min Act: -0.1700
Data Index: 1486099 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7614. Min Range: -3.7614
Max Act: 3.5736. Min Act: -0.1700
Data Index: 1876035 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19