Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3416 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5010. Min Range: -7.5010
Max Act: 7.5010. Min Act: -0.1700
Data Index: 96423 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5010. Min Range: -7.5010
Max Act: 7.2198. Min Act: -0.1700
Data Index: 88257 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5010. Min Range: -7.5010
Max Act: 7.0948. Min Act: -0.1700
Data Index: 4136993 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5010. Min Range: -7.5010
Max Act: 7.0948. Min Act: -0.1699
Data Index: 5892597 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5010. Min Range: -7.5010
Max Act: 7.0635. Min Act: -0.1700
Data Index: 3989740 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5010. Min Range: -7.5010
Max Act: 7.0635. Min Act: -0.1700
Data Index: 439197 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5010. Min Range: -7.5010
Max Act: 7.0010. Min Act: -0.1700
Data Index: 4645536 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5010. Min Range: -7.5010
Max Act: 7.0010. Min Act: -0.1700
Data Index: 1612664 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5010. Min Range: -7.5010
Max Act: 7.0010. Min Act: -0.1700
Data Index: 7372346 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5010. Min Range: -7.5010
Max Act: 6.9385. Min Act: -0.1700
Data Index: 4921801 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5010. Min Range: -7.5010
Max Act: 6.9698. Min Act: -0.1700
Data Index: 8451900 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5010. Min Range: -7.5010
Max Act: 6.9385. Min Act: -0.1700
Data Index: 3162406 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5010. Min Range: -7.5010
Max Act: 6.9385. Min Act: -0.1700
Data Index: 8663839 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5010. Min Range: -7.5010
Max Act: 6.9385. Min Act: -0.1700
Data Index: 6801005 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5010. Min Range: -7.5010
Max Act: 6.9385. Min Act: -0.1700
Data Index: 3382338 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5010. Min Range: -7.5010
Max Act: 6.9385. Min Act: -0.1700
Data Index: 315599 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5010. Min Range: -7.5010
Max Act: 6.9073. Min Act: -0.1700
Data Index: 3749852 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5010. Min Range: -7.5010
Max Act: 6.9073. Min Act: -0.1700
Data Index: 1422934 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5010. Min Range: -7.5010
Max Act: 6.8760. Min Act: -0.1700
Data Index: 6052483 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5010. Min Range: -7.5010
Max Act: 6.9073. Min Act: -0.1700
Data Index: 6645595 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #19