Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 921 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2305. Min Range: -7.2305
Max Act: 7.2305. Min Act: -0.1700
Data Index: 2187161 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2305. Min Range: -7.2305
Max Act: 7.1992. Min Act: -0.1700
Data Index: 4807415 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2305. Min Range: -7.2305
Max Act: 7.1367. Min Act: -0.1700
Data Index: 6952813 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2305. Min Range: -7.2305
Max Act: 7.1680. Min Act: -0.1700
Data Index: 7547369 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2305. Min Range: -7.2305
Max Act: 7.1367. Min Act: -0.1700
Data Index: 7301150 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2305. Min Range: -7.2305
Max Act: 7.0742. Min Act: -0.1700
Data Index: 3495701 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2305. Min Range: -7.2305
Max Act: 7.0742. Min Act: -0.1700
Data Index: 5720160 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2305. Min Range: -7.2305
Max Act: 7.0430. Min Act: -0.1700
Data Index: 8586131 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2305. Min Range: -7.2305
Max Act: 7.0430. Min Act: -0.1700
Data Index: 8274509 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2305. Min Range: -7.2305
Max Act: 7.0117. Min Act: -0.1700
Data Index: 8164950 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2305. Min Range: -7.2305
Max Act: 6.9805. Min Act: -0.1700
Data Index: 3244245 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2305. Min Range: -7.2305
Max Act: 6.9805. Min Act: -0.1700
Data Index: 4445509 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2305. Min Range: -7.2305
Max Act: 6.9492. Min Act: -0.1700
Data Index: 7382858 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2305. Min Range: -7.2305
Max Act: 6.9492. Min Act: -0.1700
Data Index: 6095247 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2305. Min Range: -7.2305
Max Act: 6.9492. Min Act: -0.1700
Data Index: 6859429 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2305. Min Range: -7.2305
Max Act: 6.9492. Min Act: -0.1700
Data Index: 6401373 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2305. Min Range: -7.2305
Max Act: 6.8555. Min Act: -0.1700
Data Index: 2549769 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2305. Min Range: -7.2305
Max Act: 6.8867. Min Act: -0.1700
Data Index: 5959860 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2305. Min Range: -7.2305
Max Act: 6.9180. Min Act: -0.1700
Data Index: 1148185 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2305. Min Range: -7.2305
Max Act: 6.8867. Min Act: -0.1700
Data Index: 8689214 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #19