Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 19 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.8968. Min Range: -3.8968
Max Act: 3.8968. Min Act: -0.1700
Data Index: 6651653 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8968. Min Range: -3.8968
Max Act: 3.8655. Min Act: -0.1700
Data Index: 4703816 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8968. Min Range: -3.8968
Max Act: 3.8029. Min Act: -0.1700
Data Index: 6343481 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8968. Min Range: -3.8968
Max Act: 3.7717. Min Act: -0.1700
Data Index: 6141936 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8968. Min Range: -3.8968
Max Act: 3.7404. Min Act: -0.1700
Data Index: 6437435 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8968. Min Range: -3.8968
Max Act: 3.7404. Min Act: -0.1700
Data Index: 6345887 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8968. Min Range: -3.8968
Max Act: 3.7404. Min Act: -0.1700
Data Index: 1778975 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8968. Min Range: -3.8968
Max Act: 3.7404. Min Act: -0.1700
Data Index: 732082 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8968. Min Range: -3.8968
Max Act: 3.7404. Min Act: -0.1700
Data Index: 7956165 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8968. Min Range: -3.8968
Max Act: 3.7404. Min Act: -0.1700
Data Index: 7545573 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8968. Min Range: -3.8968
Max Act: 3.7404. Min Act: -0.1700
Data Index: 4329854 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8968. Min Range: -3.8968
Max Act: 3.7404. Min Act: -0.1700
Data Index: 8616420 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8968. Min Range: -3.8968
Max Act: 3.7404. Min Act: -0.1700
Data Index: 3279189 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8968. Min Range: -3.8968
Max Act: 3.7091. Min Act: -0.1700
Data Index: 6293816 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8968. Min Range: -3.8968
Max Act: 3.6778. Min Act: -0.1700
Data Index: 4656410 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8968. Min Range: -3.8968
Max Act: 3.6465. Min Act: -0.1698
Data Index: 6483700 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8968. Min Range: -3.8968
Max Act: 3.6465. Min Act: -0.1700
Data Index: 5837122 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8968. Min Range: -3.8968
Max Act: 3.6465. Min Act: -0.1700
Data Index: 1368188 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8968. Min Range: -3.8968
Max Act: 3.6465. Min Act: -0.1700
Data Index: 888102 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8968. Min Range: -3.8968
Max Act: 3.6465. Min Act: -0.1700
Data Index: 6663567 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #19