Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2222 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7833. Min Range: -7.7833
Max Act: 7.7833. Min Act: -0.1700
Data Index: 2806054 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7833. Min Range: -7.7833
Max Act: 7.3458. Min Act: -0.1700
Data Index: 211049 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7833. Min Range: -7.7833
Max Act: 6.9083. Min Act: -0.1700
Data Index: 7791901 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7833. Min Range: -7.7833
Max Act: 6.9083. Min Act: -0.1700
Data Index: 4070167 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7833. Min Range: -7.7833
Max Act: 6.8146. Min Act: -0.1700
Data Index: 5151718 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7833. Min Range: -7.7833
Max Act: 6.7833. Min Act: -0.1700
Data Index: 7519551 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7833. Min Range: -7.7833
Max Act: 6.7833. Min Act: -0.1700
Data Index: 3040549 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7833. Min Range: -7.7833
Max Act: 6.8146. Min Act: -0.1700
Data Index: 342763 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7833. Min Range: -7.7833
Max Act: 6.7833. Min Act: -0.1700
Data Index: 3901587 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7833. Min Range: -7.7833
Max Act: 6.6896. Min Act: -0.1700
Data Index: 1043357 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7833. Min Range: -7.7833
Max Act: 6.6896. Min Act: -0.1700
Data Index: 3043196 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7833. Min Range: -7.7833
Max Act: 6.6896. Min Act: -0.1700
Data Index: 1129367 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7833. Min Range: -7.7833
Max Act: 6.6583. Min Act: -0.1700
Data Index: 924402 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7833. Min Range: -7.7833
Max Act: 6.6271. Min Act: -0.1700
Data Index: 60696 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7833. Min Range: -7.7833
Max Act: 6.5958. Min Act: -0.1700
Data Index: 1642113 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7833. Min Range: -7.7833
Max Act: 6.6583. Min Act: -0.1700
Data Index: 2162298 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7833. Min Range: -7.7833
Max Act: 6.6271. Min Act: -0.1700
Data Index: 4841343 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7833. Min Range: -7.7833
Max Act: 6.5958. Min Act: -0.1700
Data Index: 7032739 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7833. Min Range: -7.7833
Max Act: 6.5958. Min Act: -0.1700
Data Index: 6558662 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7833. Min Range: -7.7833
Max Act: 6.5958. Min Act: -0.1700
Data Index: 594371 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #19