Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6391 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.5096. Min Range: -3.5096
Max Act: 3.5096. Min Act: -0.1700
Data Index: 5520485 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5096. Min Range: -3.5096
Max Act: 3.3843. Min Act: -0.1700
Data Index: 7676869 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5096. Min Range: -3.5096
Max Act: 3.3058. Min Act: -0.1700
Data Index: 973439 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5096. Min Range: -3.5096
Max Act: 3.3058. Min Act: -0.1700
Data Index: 265421 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5096. Min Range: -3.5096
Max Act: 3.2587. Min Act: -0.1700
Data Index: 6481641 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5096. Min Range: -3.5096
Max Act: 3.2744. Min Act: -0.1700
Data Index: 851036 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5096. Min Range: -3.5096
Max Act: 3.2430. Min Act: -0.1700
Data Index: 4522969 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5096. Min Range: -3.5096
Max Act: 3.2273. Min Act: -0.1700
Data Index: 2489402 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5096. Min Range: -3.5096
Max Act: 3.2587. Min Act: -0.1700
Data Index: 6961918 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5096. Min Range: -3.5096
Max Act: 3.2430. Min Act: -0.1700
Data Index: 646019 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5096. Min Range: -3.5096
Max Act: 3.2116. Min Act: -0.1699
Data Index: 3352807 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5096. Min Range: -3.5096
Max Act: 3.2116. Min Act: -0.1699
Data Index: 2274606 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5096. Min Range: -3.5096
Max Act: 3.2273. Min Act: -0.1700
Data Index: 2348331 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5096. Min Range: -3.5096
Max Act: 3.1959. Min Act: -0.1700
Data Index: 1139877 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5096. Min Range: -3.5096
Max Act: 3.1487. Min Act: -0.1700
Data Index: 7743489 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5096. Min Range: -3.5096
Max Act: 3.1959. Min Act: -0.1700
Data Index: 994955 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5096. Min Range: -3.5096
Max Act: 3.1801. Min Act: -0.1700
Data Index: 5340861 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5096. Min Range: -3.5096
Max Act: 3.1644. Min Act: -0.1700
Data Index: 2992615 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5096. Min Range: -3.5096
Max Act: 3.1644. Min Act: -0.1700
Data Index: 2138891 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5096. Min Range: -3.5096
Max Act: 3.1644. Min Act: -0.1699
Data Index: 6692660 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #19