Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2709 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8699. Min Range: -7.8699
Max Act: 7.8699. Min Act: -0.1700
Data Index: 2866817 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8699. Min Range: -7.8699
Max Act: 7.6199. Min Act: -0.1700
Data Index: 2116794 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8699. Min Range: -7.8699
Max Act: 7.4637. Min Act: -0.1700
Data Index: 6199471 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8699. Min Range: -7.8699
Max Act: 7.4324. Min Act: -0.1700
Data Index: 1101032 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8699. Min Range: -7.8699
Max Act: 7.4012. Min Act: -0.1700
Data Index: 6035609 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8699. Min Range: -7.8699
Max Act: 7.3699. Min Act: -0.1700
Data Index: 7731012 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8699. Min Range: -7.8699
Max Act: 7.3074. Min Act: -0.1700
Data Index: 4972038 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8699. Min Range: -7.8699
Max Act: 7.2762. Min Act: -0.1700
Data Index: 1751382 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8699. Min Range: -7.8699
Max Act: 7.3074. Min Act: -0.1700
Data Index: 7985282 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8699. Min Range: -7.8699
Max Act: 7.2762. Min Act: -0.1700
Data Index: 2707681 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8699. Min Range: -7.8699
Max Act: 7.2762. Min Act: -0.1700
Data Index: 8586627 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8699. Min Range: -7.8699
Max Act: 7.2762. Min Act: -0.1700
Data Index: 6635597 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8699. Min Range: -7.8699
Max Act: 7.2449. Min Act: -0.1700
Data Index: 1189827 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8699. Min Range: -7.8699
Max Act: 7.2762. Min Act: -0.1700
Data Index: 6180845 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8699. Min Range: -7.8699
Max Act: 7.2137. Min Act: -0.1700
Data Index: 7552744 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8699. Min Range: -7.8699
Max Act: 7.2137. Min Act: -0.1700
Data Index: 1353117 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8699. Min Range: -7.8699
Max Act: 7.2137. Min Act: -0.1700
Data Index: 6612520 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8699. Min Range: -7.8699
Max Act: 7.2137. Min Act: -0.1700
Data Index: 6991142 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8699. Min Range: -7.8699
Max Act: 7.2449. Min Act: -0.1700
Data Index: 3419241 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8699. Min Range: -7.8699
Max Act: 7.1824. Min Act: -0.1700
Data Index: 5804135 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #19