Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 157 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6080. Min Range: -4.6080
Max Act: 4.6080. Min Act: -0.1700
Data Index: 8310551 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6080. Min Range: -4.6080
Max Act: 4.5455. Min Act: -0.1700
Data Index: 142007 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6080. Min Range: -4.6080
Max Act: 4.5143. Min Act: -0.1700
Data Index: 8306714 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6080. Min Range: -4.6080
Max Act: 4.4517. Min Act: -0.1700
Data Index: 6341054 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6080. Min Range: -4.6080
Max Act: 4.3580. Min Act: -0.1700
Data Index: 8283254 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6080. Min Range: -4.6080
Max Act: 4.3580. Min Act: -0.1700
Data Index: 8174966 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6080. Min Range: -4.6080
Max Act: 4.3580. Min Act: -0.1700
Data Index: 6418220 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6080. Min Range: -4.6080
Max Act: 4.2955. Min Act: -0.1700
Data Index: 8083422 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6080. Min Range: -4.6080
Max Act: 4.2642. Min Act: -0.1700
Data Index: 6948421 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6080. Min Range: -4.6080
Max Act: 4.2330. Min Act: -0.1700
Data Index: 5657119 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6080. Min Range: -4.6080
Max Act: 4.2330. Min Act: -0.1700
Data Index: 2192439 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6080. Min Range: -4.6080
Max Act: 4.2330. Min Act: -0.1700
Data Index: 6870358 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6080. Min Range: -4.6080
Max Act: 4.2017. Min Act: -0.1700
Data Index: 137722 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6080. Min Range: -4.6080
Max Act: 4.2017. Min Act: -0.1700
Data Index: 6711811 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6080. Min Range: -4.6080
Max Act: 4.2017. Min Act: -0.1700
Data Index: 1960038 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6080. Min Range: -4.6080
Max Act: 4.1705. Min Act: -0.1700
Data Index: 4081617 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6080. Min Range: -4.6080
Max Act: 4.1705. Min Act: -0.1700
Data Index: 2304949 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6080. Min Range: -4.6080
Max Act: 4.1705. Min Act: -0.1700
Data Index: 3569963 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6080. Min Range: -4.6080
Max Act: 4.1705. Min Act: -0.1700
Data Index: 2231441 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6080. Min Range: -4.6080
Max Act: 4.1392. Min Act: -0.1700
Data Index: 3448771 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #19