Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 207 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.9187. Min Range: -8.9187
Max Act: 8.9187. Min Act: -0.1700
Data Index: 1301303 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.9187. Min Range: -8.9187
Max Act: 8.9187. Min Act: -0.1700
Data Index: 7714508 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.9187. Min Range: -8.9187
Max Act: 8.9187. Min Act: -0.1700
Data Index: 7411630 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.9187. Min Range: -8.9187
Max Act: 8.7937. Min Act: -0.1700
Data Index: 7525879 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.9187. Min Range: -8.9187
Max Act: 8.7937. Min Act: -0.1700
Data Index: 4824129 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.9187. Min Range: -8.9187
Max Act: 8.7312. Min Act: -0.1700
Data Index: 8723458 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.9187. Min Range: -8.9187
Max Act: 8.7312. Min Act: -0.1700
Data Index: 519686 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.9187. Min Range: -8.9187
Max Act: 8.7312. Min Act: -0.1700
Data Index: 5100997 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.9187. Min Range: -8.9187
Max Act: 8.7312. Min Act: -0.1700
Data Index: 5017964 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.9187. Min Range: -8.9187
Max Act: 8.7312. Min Act: -0.1700
Data Index: 2918401 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.9187. Min Range: -8.9187
Max Act: 8.6687. Min Act: -0.1700
Data Index: 8154763 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.9187. Min Range: -8.9187
Max Act: 8.6687. Min Act: -0.1700
Data Index: 3899461 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.9187. Min Range: -8.9187
Max Act: 8.6687. Min Act: -0.1700
Data Index: 8796765 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.9187. Min Range: -8.9187
Max Act: 8.6687. Min Act: -0.1700
Data Index: 7224427 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.9187. Min Range: -8.9187
Max Act: 8.6687. Min Act: -0.1700
Data Index: 653321 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.9187. Min Range: -8.9187
Max Act: 8.6687. Min Act: -0.1700
Data Index: 4772097 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.9187. Min Range: -8.9187
Max Act: 8.6687. Min Act: -0.1700
Data Index: 7949316 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.9187. Min Range: -8.9187
Max Act: 8.6062. Min Act: -0.1700
Data Index: 3198330 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.9187. Min Range: -8.9187
Max Act: 8.6062. Min Act: -0.1700
Data Index: 1183125 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.9187. Min Range: -8.9187
Max Act: 8.6062. Min Act: -0.1700
Data Index: 2787955 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #19