Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4619 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.7208. Min Range: -8.7208
Max Act: 8.7208. Min Act: -0.1700
Data Index: 4468550 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7208. Min Range: -8.7208
Max Act: 8.7208. Min Act: -0.1700
Data Index: 978313 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7208. Min Range: -8.7208
Max Act: 8.5333. Min Act: -0.1700
Data Index: 7655166 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7208. Min Range: -8.7208
Max Act: 8.3458. Min Act: -0.1700
Data Index: 7262868 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7208. Min Range: -8.7208
Max Act: 8.2833. Min Act: -0.1700
Data Index: 1462350 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7208. Min Range: -8.7208
Max Act: 8.1583. Min Act: -0.1700
Data Index: 4388363 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7208. Min Range: -8.7208
Max Act: 8.1583. Min Act: -0.1700
Data Index: 5395778 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7208. Min Range: -8.7208
Max Act: 8.1583. Min Act: -0.1700
Data Index: 2563106 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7208. Min Range: -8.7208
Max Act: 8.0958. Min Act: -0.1700
Data Index: 7655188 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7208. Min Range: -8.7208
Max Act: 8.0958. Min Act: -0.1700
Data Index: 390821 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7208. Min Range: -8.7208
Max Act: 8.0333. Min Act: -0.1700
Data Index: 468698 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7208. Min Range: -8.7208
Max Act: 7.9708. Min Act: -0.1700
Data Index: 8266135 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7208. Min Range: -8.7208
Max Act: 7.9708. Min Act: -0.1700
Data Index: 4500579 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7208. Min Range: -8.7208
Max Act: 7.9083. Min Act: -0.1700
Data Index: 5213734 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7208. Min Range: -8.7208
Max Act: 7.9083. Min Act: -0.1700
Data Index: 1371477 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7208. Min Range: -8.7208
Max Act: 7.9083. Min Act: -0.1700
Data Index: 8198763 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7208. Min Range: -8.7208
Max Act: 7.9083. Min Act: -0.1700
Data Index: 5253678 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7208. Min Range: -8.7208
Max Act: 7.8458. Min Act: -0.1700
Data Index: 6627914 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7208. Min Range: -8.7208
Max Act: 7.8458. Min Act: -0.1700
Data Index: 5161732 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7208. Min Range: -8.7208
Max Act: 7.7833. Min Act: -0.1700
Data Index: 5611597 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #19