Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1939 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3807. Min Range: -5.3807
Max Act: 5.3807. Min Act: -0.1700
Data Index: 4501117 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3807. Min Range: -5.3807
Max Act: 5.3494. Min Act: -0.1700
Data Index: 5175613 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3807. Min Range: -5.3807
Max Act: 5.3494. Min Act: -0.1700
Data Index: 1764605 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3807. Min Range: -5.3807
Max Act: 5.3182. Min Act: -0.1700
Data Index: 7211066 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3807. Min Range: -5.3807
Max Act: 5.3494. Min Act: -0.1700
Data Index: 5547769 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3807. Min Range: -5.3807
Max Act: 5.2557. Min Act: -0.1700
Data Index: 2265574 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3807. Min Range: -5.3807
Max Act: 5.2869. Min Act: -0.1700
Data Index: 366369 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3807. Min Range: -5.3807
Max Act: 5.2557. Min Act: -0.1700
Data Index: 4795626 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3807. Min Range: -5.3807
Max Act: 5.2557. Min Act: -0.1700
Data Index: 7175588 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3807. Min Range: -5.3807
Max Act: 5.2244. Min Act: -0.1700
Data Index: 7211075 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3807. Min Range: -5.3807
Max Act: 5.2244. Min Act: -0.1700
Data Index: 812701 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3807. Min Range: -5.3807
Max Act: 5.1932. Min Act: -0.1700
Data Index: 8397216 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3807. Min Range: -5.3807
Max Act: 5.1932. Min Act: -0.1700
Data Index: 4383759 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3807. Min Range: -5.3807
Max Act: 5.1932. Min Act: -0.1700
Data Index: 181260 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3807. Min Range: -5.3807
Max Act: 5.1619. Min Act: -0.1700
Data Index: 1238615 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3807. Min Range: -5.3807
Max Act: 5.1619. Min Act: -0.1700
Data Index: 4501859 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3807. Min Range: -5.3807
Max Act: 5.1619. Min Act: -0.1700
Data Index: 7028728 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3807. Min Range: -5.3807
Max Act: 5.1619. Min Act: -0.1700
Data Index: 2265573 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3807. Min Range: -5.3807
Max Act: 5.1619. Min Act: -0.1700
Data Index: 3387952 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3807. Min Range: -5.3807
Max Act: 5.1619. Min Act: -0.1700
Data Index: 2122740 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #19