Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3497 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1957. Min Range: -5.1957
Max Act: 5.1957. Min Act: -0.1700
Data Index: 8724381 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1957. Min Range: -5.1957
Max Act: 5.0394. Min Act: -0.1700
Data Index: 3758631 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1957. Min Range: -5.1957
Max Act: 4.9769. Min Act: -0.1700
Data Index: 3899958 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1957. Min Range: -5.1957
Max Act: 4.9769. Min Act: -0.1700
Data Index: 345200 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1957. Min Range: -5.1957
Max Act: 4.9457. Min Act: -0.1700
Data Index: 301164 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1957. Min Range: -5.1957
Max Act: 4.9769. Min Act: -0.1700
Data Index: 6003572 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1957. Min Range: -5.1957
Max Act: 4.9144. Min Act: -0.1700
Data Index: 401671 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1957. Min Range: -5.1957
Max Act: 4.9144. Min Act: -0.1700
Data Index: 3094178 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1957. Min Range: -5.1957
Max Act: 4.9144. Min Act: -0.1700
Data Index: 2534315 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1957. Min Range: -5.1957
Max Act: 4.8832. Min Act: -0.1700
Data Index: 326585 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1957. Min Range: -5.1957
Max Act: 4.8519. Min Act: -0.1700
Data Index: 2276289 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1957. Min Range: -5.1957
Max Act: 4.8207. Min Act: -0.1700
Data Index: 123696 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1957. Min Range: -5.1957
Max Act: 4.8207. Min Act: -0.1700
Data Index: 7939887 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1957. Min Range: -5.1957
Max Act: 4.8207. Min Act: -0.1700
Data Index: 5113038 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1957. Min Range: -5.1957
Max Act: 4.8207. Min Act: -0.1700
Data Index: 8702290 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1957. Min Range: -5.1957
Max Act: 4.8207. Min Act: -0.1700
Data Index: 6641881 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1957. Min Range: -5.1957
Max Act: 4.7894. Min Act: -0.1700
Data Index: 3849150 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1957. Min Range: -5.1957
Max Act: 4.7894. Min Act: -0.1700
Data Index: 2011193 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1957. Min Range: -5.1957
Max Act: 4.7894. Min Act: -0.1700
Data Index: 8384610 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1957. Min Range: -5.1957
Max Act: 4.7894. Min Act: -0.1700
Data Index: 105453 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #19