Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2886 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8060. Min Range: -3.8060
Max Act: 3.8060. Min Act: -0.1700
Data Index: 6543665 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8060. Min Range: -3.8060
Max Act: 3.8060. Min Act: -0.1700
Data Index: 6820313 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8060. Min Range: -3.8060
Max Act: 3.6027. Min Act: -0.1700
Data Index: 1653191 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8060. Min Range: -3.8060
Max Act: 3.5400. Min Act: -0.1700
Data Index: 6392541 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8060. Min Range: -3.8060
Max Act: 3.4617. Min Act: -0.1700
Data Index: 1050967 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8060. Min Range: -3.8060
Max Act: 3.3520. Min Act: -0.1700
Data Index: 8814736 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8060. Min Range: -3.8060
Max Act: 3.3206. Min Act: -0.1700
Data Index: 6361331 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8060. Min Range: -3.8060
Max Act: 3.3049. Min Act: -0.1700
Data Index: 2108789 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8060. Min Range: -3.8060
Max Act: 3.3206. Min Act: -0.1700
Data Index: 1736881 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8060. Min Range: -3.8060
Max Act: 3.2735. Min Act: -0.1700
Data Index: 6120737 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8060. Min Range: -3.8060
Max Act: 3.2735. Min Act: -0.1700
Data Index: 7808614 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8060. Min Range: -3.8060
Max Act: 3.2735. Min Act: -0.1700
Data Index: 4396531 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8060. Min Range: -3.8060
Max Act: 3.2735. Min Act: -0.1700
Data Index: 1561812 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8060. Min Range: -3.8060
Max Act: 3.2578. Min Act: -0.1700
Data Index: 8199699 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8060. Min Range: -3.8060
Max Act: 3.2578. Min Act: -0.1700
Data Index: 6737279 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8060. Min Range: -3.8060
Max Act: 3.2264. Min Act: -0.1700
Data Index: 7990799 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8060. Min Range: -3.8060
Max Act: 3.2107. Min Act: -0.1700
Data Index: 4691234 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8060. Min Range: -3.8060
Max Act: 3.2107. Min Act: -0.1700
Data Index: 6048861 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8060. Min Range: -3.8060
Max Act: 3.1949. Min Act: -0.1700
Data Index: 7851718 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8060. Min Range: -3.8060
Max Act: 3.1792. Min Act: -0.1700
Data Index: 6904029 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #19