Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2878 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.2427. Min Range: -4.2427
Max Act: 4.2427. Min Act: -0.1700
Data Index: 7405742 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2427. Min Range: -4.2427
Max Act: 4.1177. Min Act: -0.1700
Data Index: 5708565 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2427. Min Range: -4.2427
Max Act: 4.1177. Min Act: -0.1700
Data Index: 7335987 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2427. Min Range: -4.2427
Max Act: 4.1177. Min Act: -0.1700
Data Index: 7405743 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2427. Min Range: -4.2427
Max Act: 4.1177. Min Act: -0.1700
Data Index: 7782740 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2427. Min Range: -4.2427
Max Act: 4.1177. Min Act: -0.1700
Data Index: 2923296 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2427. Min Range: -4.2427
Max Act: 4.1177. Min Act: -0.1700
Data Index: 3388542 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2427. Min Range: -4.2427
Max Act: 4.0864. Min Act: -0.1700
Data Index: 884168 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2427. Min Range: -4.2427
Max Act: 4.0551. Min Act: -0.1700
Data Index: 3873328 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2427. Min Range: -4.2427
Max Act: 4.0551. Min Act: -0.1700
Data Index: 7405740 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2427. Min Range: -4.2427
Max Act: 4.0551. Min Act: -0.1700
Data Index: 4697576 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2427. Min Range: -4.2427
Max Act: 3.9926. Min Act: -0.1700
Data Index: 6561165 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2427. Min Range: -4.2427
Max Act: 3.9926. Min Act: -0.1700
Data Index: 4923367 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2427. Min Range: -4.2427
Max Act: 3.9926. Min Act: -0.1700
Data Index: 995601 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2427. Min Range: -4.2427
Max Act: 3.9926. Min Act: -0.1700
Data Index: 824759 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2427. Min Range: -4.2427
Max Act: 3.9926. Min Act: -0.1700
Data Index: 8214238 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2427. Min Range: -4.2427
Max Act: 3.9926. Min Act: -0.1700
Data Index: 733136 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2427. Min Range: -4.2427
Max Act: 3.9614. Min Act: -0.1700
Data Index: 1276179 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2427. Min Range: -4.2427
Max Act: 3.9614. Min Act: -0.1700
Data Index: 2051988 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2427. Min Range: -4.2427
Max Act: 3.9614. Min Act: -0.1700
Data Index: 3864375 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #19