Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4987 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0047. Min Range: -7.0047
Max Act: 7.0047. Min Act: -0.1700
Data Index: 1804176 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0047. Min Range: -7.0047
Max Act: 7.0047. Min Act: -0.1700
Data Index: 4543223 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0047. Min Range: -7.0047
Max Act: 6.9422. Min Act: -0.1700
Data Index: 6755369 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0047. Min Range: -7.0047
Max Act: 6.9422. Min Act: -0.1700
Data Index: 5548488 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0047. Min Range: -7.0047
Max Act: 6.9422. Min Act: -0.1700
Data Index: 1400494 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0047. Min Range: -7.0047
Max Act: 6.9110. Min Act: -0.1699
Data Index: 4584708 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0047. Min Range: -7.0047
Max Act: 6.9110. Min Act: -0.1700
Data Index: 4945442 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0047. Min Range: -7.0047
Max Act: 6.9110. Min Act: -0.1700
Data Index: 2819951 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0047. Min Range: -7.0047
Max Act: 6.9422. Min Act: -0.1700
Data Index: 8079284 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0047. Min Range: -7.0047
Max Act: 6.8797. Min Act: -0.1700
Data Index: 4642965 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0047. Min Range: -7.0047
Max Act: 6.8797. Min Act: -0.1700
Data Index: 4407148 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0047. Min Range: -7.0047
Max Act: 6.8797. Min Act: -0.1700
Data Index: 5170906 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0047. Min Range: -7.0047
Max Act: 6.8797. Min Act: -0.1700
Data Index: 5363395 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0047. Min Range: -7.0047
Max Act: 6.8797. Min Act: -0.1700
Data Index: 78201 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0047. Min Range: -7.0047
Max Act: 6.8797. Min Act: -0.1700
Data Index: 5602149 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0047. Min Range: -7.0047
Max Act: 6.8797. Min Act: -0.1700
Data Index: 5758155 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0047. Min Range: -7.0047
Max Act: 6.8485. Min Act: -0.1700
Data Index: 6572163 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0047. Min Range: -7.0047
Max Act: 6.8797. Min Act: -0.1700
Data Index: 6587825 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0047. Min Range: -7.0047
Max Act: 6.8797. Min Act: -0.1699
Data Index: 6641019 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0047. Min Range: -7.0047
Max Act: 6.8797. Min Act: -0.1700
Data Index: 6672292 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #19