Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1677 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.1970. Min Range: -10.1970
Max Act: 10.1970. Min Act: -0.1700
Data Index: 4033053 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.1970. Min Range: -10.1970
Max Act: 10.1345. Min Act: -0.1700
Data Index: 519453 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.1970. Min Range: -10.1970
Max Act: 10.0095. Min Act: -0.1700
Data Index: 4242917 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.1970. Min Range: -10.1970
Max Act: 10.0720. Min Act: -0.1700
Data Index: 3328809 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.1970. Min Range: -10.1970
Max Act: 10.0720. Min Act: -0.1700
Data Index: 1593269 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.1970. Min Range: -10.1970
Max Act: 10.0095. Min Act: -0.1700
Data Index: 1740982 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.1970. Min Range: -10.1970
Max Act: 10.0095. Min Act: -0.1700
Data Index: 8159629 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.1970. Min Range: -10.1970
Max Act: 9.9470. Min Act: -0.1700
Data Index: 8087884 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.1970. Min Range: -10.1970
Max Act: 9.9470. Min Act: -0.1700
Data Index: 8497252 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.1970. Min Range: -10.1970
Max Act: 9.8845. Min Act: -0.1700
Data Index: 5940943 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.1970. Min Range: -10.1970
Max Act: 9.8845. Min Act: -0.1700
Data Index: 5894280 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.1970. Min Range: -10.1970
Max Act: 9.8845. Min Act: -0.1700
Data Index: 3225607 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.1970. Min Range: -10.1970
Max Act: 9.8845. Min Act: -0.1700
Data Index: 1073062 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.1970. Min Range: -10.1970
Max Act: 9.8845. Min Act: -0.1700
Data Index: 3660669 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.1970. Min Range: -10.1970
Max Act: 9.8845. Min Act: -0.1700
Data Index: 6363098 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.1970. Min Range: -10.1970
Max Act: 9.7595. Min Act: -0.1700
Data Index: 3951224 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.1970. Min Range: -10.1970
Max Act: 9.8220. Min Act: -0.1700
Data Index: 4341617 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.1970. Min Range: -10.1970
Max Act: 9.8220. Min Act: -0.1700
Data Index: 6105390 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.1970. Min Range: -10.1970
Max Act: 9.8220. Min Act: -0.1700
Data Index: 861555 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.1970. Min Range: -10.1970
Max Act: 9.7595. Min Act: -0.1700
Data Index: 4901262 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #19