Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3503 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1681. Min Range: -5.1681
Max Act: 5.1681. Min Act: -0.1700
Data Index: 5591140 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1681. Min Range: -5.1681
Max Act: 5.1681. Min Act: -0.1700
Data Index: 5184758 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1681. Min Range: -5.1681
Max Act: 5.1681. Min Act: -0.1700
Data Index: 968708 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1681. Min Range: -5.1681
Max Act: 5.1681. Min Act: -0.1700
Data Index: 5253971 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1681. Min Range: -5.1681
Max Act: 5.1056. Min Act: -0.1700
Data Index: 472774 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1681. Min Range: -5.1681
Max Act: 5.0743. Min Act: -0.1700
Data Index: 2832592 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1681. Min Range: -5.1681
Max Act: 5.0743. Min Act: -0.1700
Data Index: 8350976 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1681. Min Range: -5.1681
Max Act: 5.0431. Min Act: -0.1700
Data Index: 2183896 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1681. Min Range: -5.1681
Max Act: 5.0431. Min Act: -0.1700
Data Index: 1737457 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1681. Min Range: -5.1681
Max Act: 5.0118. Min Act: -0.1700
Data Index: 8008197 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1681. Min Range: -5.1681
Max Act: 5.0431. Min Act: -0.1700
Data Index: 6620818 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1681. Min Range: -5.1681
Max Act: 4.9806. Min Act: -0.1700
Data Index: 88903 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1681. Min Range: -5.1681
Max Act: 4.9806. Min Act: -0.1700
Data Index: 3511533 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1681. Min Range: -5.1681
Max Act: 4.9806. Min Act: -0.1700
Data Index: 7150398 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1681. Min Range: -5.1681
Max Act: 4.9493. Min Act: -0.1700
Data Index: 763171 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1681. Min Range: -5.1681
Max Act: 4.9806. Min Act: -0.1700
Data Index: 5254010 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1681. Min Range: -5.1681
Max Act: 4.9806. Min Act: -0.1700
Data Index: 8190694 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1681. Min Range: -5.1681
Max Act: 4.9806. Min Act: -0.1700
Data Index: 1547523 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1681. Min Range: -5.1681
Max Act: 4.9493. Min Act: -0.1700
Data Index: 5204101 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1681. Min Range: -5.1681
Max Act: 4.9806. Min Act: -0.1700
Data Index: 1990460 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #19