Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 146 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0880. Min Range: -8.0880
Max Act: 8.0880. Min Act: -0.1700
Data Index: 1737243 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0880. Min Range: -8.0880
Max Act: 7.8380. Min Act: -0.1700
Data Index: 3137682 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0880. Min Range: -8.0880
Max Act: 7.8692. Min Act: -0.1700
Data Index: 6379321 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0880. Min Range: -8.0880
Max Act: 7.8067. Min Act: -0.1700
Data Index: 5326751 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0880. Min Range: -8.0880
Max Act: 7.7755. Min Act: -0.1700
Data Index: 6000760 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0880. Min Range: -8.0880
Max Act: 7.7442. Min Act: -0.1700
Data Index: 8776398 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0880. Min Range: -8.0880
Max Act: 7.7442. Min Act: -0.1700
Data Index: 4549796 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0880. Min Range: -8.0880
Max Act: 7.7130. Min Act: -0.1700
Data Index: 2908997 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0880. Min Range: -8.0880
Max Act: 7.5880. Min Act: -0.1700
Data Index: 218270 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0880. Min Range: -8.0880
Max Act: 7.4942. Min Act: -0.1700
Data Index: 121375 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0880. Min Range: -8.0880
Max Act: 7.4317. Min Act: -0.1700
Data Index: 2379161 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0880. Min Range: -8.0880
Max Act: 7.4317. Min Act: -0.1700
Data Index: 3814241 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0880. Min Range: -8.0880
Max Act: 7.4317. Min Act: -0.1700
Data Index: 2323526 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0880. Min Range: -8.0880
Max Act: 7.4005. Min Act: -0.1700
Data Index: 980467 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0880. Min Range: -8.0880
Max Act: 7.3692. Min Act: -0.1700
Data Index: 1951057 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0880. Min Range: -8.0880
Max Act: 7.3380. Min Act: -0.1700
Data Index: 7293530 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0880. Min Range: -8.0880
Max Act: 7.3692. Min Act: -0.1700
Data Index: 6654966 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0880. Min Range: -8.0880
Max Act: 7.3380. Min Act: -0.1700
Data Index: 1718175 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0880. Min Range: -8.0880
Max Act: 7.3067. Min Act: -0.1700
Data Index: 378512 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0880. Min Range: -8.0880
Max Act: 7.3380. Min Act: -0.1700
Data Index: 356554 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #19