Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3978 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.0880. Min Range: -9.0880
Max Act: 9.0880. Min Act: -0.1700
Data Index: 610182 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.0880. Min Range: -9.0880
Max Act: 9.0255. Min Act: -0.1700
Data Index: 7617447 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.0880. Min Range: -9.0880
Max Act: 8.9005. Min Act: -0.1700
Data Index: 6037311 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.0880. Min Range: -9.0880
Max Act: 8.8380. Min Act: -0.1700
Data Index: 1308545 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.0880. Min Range: -9.0880
Max Act: 8.7755. Min Act: -0.1700
Data Index: 198915 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.0880. Min Range: -9.0880
Max Act: 8.7130. Min Act: -0.1700
Data Index: 2065758 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.0880. Min Range: -9.0880
Max Act: 8.7755. Min Act: -0.1700
Data Index: 2343613 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.0880. Min Range: -9.0880
Max Act: 8.7755. Min Act: -0.1700
Data Index: 1462506 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.0880. Min Range: -9.0880
Max Act: 8.7755. Min Act: -0.1700
Data Index: 2433141 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.0880. Min Range: -9.0880
Max Act: 8.8380. Min Act: -0.1700
Data Index: 7150541 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.0880. Min Range: -9.0880
Max Act: 8.7130. Min Act: -0.1700
Data Index: 2091220 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.0880. Min Range: -9.0880
Max Act: 8.7130. Min Act: -0.1700
Data Index: 6564212 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.0880. Min Range: -9.0880
Max Act: 8.7130. Min Act: -0.1700
Data Index: 2664010 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.0880. Min Range: -9.0880
Max Act: 8.7130. Min Act: -0.1700
Data Index: 7264869 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.0880. Min Range: -9.0880
Max Act: 8.6505. Min Act: -0.1700
Data Index: 1950887 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.0880. Min Range: -9.0880
Max Act: 8.7130. Min Act: -0.1700
Data Index: 355695 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.0880. Min Range: -9.0880
Max Act: 8.6505. Min Act: -0.1700
Data Index: 9269 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.0880. Min Range: -9.0880
Max Act: 8.6505. Min Act: -0.1700
Data Index: 3096874 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.0880. Min Range: -9.0880
Max Act: 8.5880. Min Act: -0.1700
Data Index: 2669099 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.0880. Min Range: -9.0880
Max Act: 8.6505. Min Act: -0.1700
Data Index: 2623414 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #19