Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5163 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.0034. Min Range: -9.0034
Max Act: 9.0034. Min Act: -0.1700
Data Index: 3168421 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.0034. Min Range: -9.0034
Max Act: 8.9409. Min Act: -0.1700
Data Index: 1724201 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.0034. Min Range: -9.0034
Max Act: 8.8784. Min Act: -0.1700
Data Index: 6305937 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.0034. Min Range: -9.0034
Max Act: 8.8784. Min Act: -0.1700
Data Index: 5449921 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.0034. Min Range: -9.0034
Max Act: 8.8159. Min Act: -0.1700
Data Index: 3997982 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.0034. Min Range: -9.0034
Max Act: 8.8159. Min Act: -0.1700
Data Index: 896007 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.0034. Min Range: -9.0034
Max Act: 8.8159. Min Act: -0.1700
Data Index: 8070895 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.0034. Min Range: -9.0034
Max Act: 8.6909. Min Act: -0.1700
Data Index: 1022382 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.0034. Min Range: -9.0034
Max Act: 8.6909. Min Act: -0.1700
Data Index: 3997983 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.0034. Min Range: -9.0034
Max Act: 8.6909. Min Act: -0.1700
Data Index: 1505394 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.0034. Min Range: -9.0034
Max Act: 8.5659. Min Act: -0.1700
Data Index: 8037349 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.0034. Min Range: -9.0034
Max Act: 8.5659. Min Act: -0.1700
Data Index: 4143227 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.0034. Min Range: -9.0034
Max Act: 8.5659. Min Act: -0.1700
Data Index: 5498820 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.0034. Min Range: -9.0034
Max Act: 8.3784. Min Act: -0.1700
Data Index: 6294296 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.0034. Min Range: -9.0034
Max Act: 8.4409. Min Act: -0.1700
Data Index: 8483262 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.0034. Min Range: -9.0034
Max Act: 8.3784. Min Act: -0.1700
Data Index: 3661931 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.0034. Min Range: -9.0034
Max Act: 8.3159. Min Act: -0.1700
Data Index: 5430327 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.0034. Min Range: -9.0034
Max Act: 8.3159. Min Act: -0.1700
Data Index: 4025269 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.0034. Min Range: -9.0034
Max Act: 8.3159. Min Act: -0.1700
Data Index: 6319468 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.0034. Min Range: -9.0034
Max Act: 8.3784. Min Act: -0.1700
Data Index: 1795623 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #19