Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1957 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5205. Min Range: -4.5205
Max Act: 4.5205. Min Act: -0.1700
Data Index: 7474509 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5205. Min Range: -4.5205
Max Act: 4.4580. Min Act: -0.1700
Data Index: 3733374 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5205. Min Range: -4.5205
Max Act: 4.4580. Min Act: -0.1700
Data Index: 4812330 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5205. Min Range: -4.5205
Max Act: 4.4580. Min Act: -0.1700
Data Index: 8339297 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5205. Min Range: -4.5205
Max Act: 4.4267. Min Act: -0.1700
Data Index: 1066375 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5205. Min Range: -4.5205
Max Act: 4.4267. Min Act: -0.1700
Data Index: 7209282 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5205. Min Range: -4.5205
Max Act: 4.3955. Min Act: -0.1700
Data Index: 6926949 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5205. Min Range: -4.5205
Max Act: 4.3955. Min Act: -0.1700
Data Index: 6630544 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5205. Min Range: -4.5205
Max Act: 4.3642. Min Act: -0.1700
Data Index: 1571693 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5205. Min Range: -4.5205
Max Act: 4.3642. Min Act: -0.1700
Data Index: 7608294 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5205. Min Range: -4.5205
Max Act: 4.3642. Min Act: -0.1700
Data Index: 6028944 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5205. Min Range: -4.5205
Max Act: 4.3642. Min Act: -0.1700
Data Index: 3224547 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5205. Min Range: -4.5205
Max Act: 4.3330. Min Act: -0.1700
Data Index: 4943137 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5205. Min Range: -4.5205
Max Act: 4.3642. Min Act: -0.1700
Data Index: 4156639 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5205. Min Range: -4.5205
Max Act: 4.3642. Min Act: -0.1700
Data Index: 8176542 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5205. Min Range: -4.5205
Max Act: 4.3330. Min Act: -0.1700
Data Index: 7602816 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5205. Min Range: -4.5205
Max Act: 4.3330. Min Act: -0.1700
Data Index: 2456513 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5205. Min Range: -4.5205
Max Act: 4.3330. Min Act: -0.1700
Data Index: 6625410 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5205. Min Range: -4.5205
Max Act: 4.3330. Min Act: -0.1700
Data Index: 7602815 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5205. Min Range: -4.5205
Max Act: 4.3330. Min Act: -0.1700
Data Index: 899119 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #19