Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3498 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2519. Min Range: -5.2519
Max Act: 5.2519. Min Act: -0.1700
Data Index: 8817405 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2519. Min Range: -5.2519
Max Act: 5.2207. Min Act: -0.1700
Data Index: 7154226 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2519. Min Range: -5.2519
Max Act: 5.1894. Min Act: -0.1700
Data Index: 8281796 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2519. Min Range: -5.2519
Max Act: 5.1582. Min Act: -0.1700
Data Index: 1356615 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2519. Min Range: -5.2519
Max Act: 5.1582. Min Act: -0.1700
Data Index: 7229658 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2519. Min Range: -5.2519
Max Act: 5.1582. Min Act: -0.1700
Data Index: 4182172 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2519. Min Range: -5.2519
Max Act: 5.1582. Min Act: -0.1700
Data Index: 1013543 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2519. Min Range: -5.2519
Max Act: 5.1582. Min Act: -0.1700
Data Index: 5428461 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2519. Min Range: -5.2519
Max Act: 5.1269. Min Act: -0.1700
Data Index: 2862107 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2519. Min Range: -5.2519
Max Act: 5.1269. Min Act: -0.1700
Data Index: 5963218 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2519. Min Range: -5.2519
Max Act: 5.1269. Min Act: -0.1700
Data Index: 2157725 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2519. Min Range: -5.2519
Max Act: 5.1269. Min Act: -0.1700
Data Index: 5834113 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2519. Min Range: -5.2519
Max Act: 5.1269. Min Act: -0.1700
Data Index: 5030719 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2519. Min Range: -5.2519
Max Act: 5.1269. Min Act: -0.1700
Data Index: 7416386 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2519. Min Range: -5.2519
Max Act: 5.1269. Min Act: -0.1700
Data Index: 1609912 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2519. Min Range: -5.2519
Max Act: 5.0957. Min Act: -0.1700
Data Index: 8522832 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2519. Min Range: -5.2519
Max Act: 5.1269. Min Act: -0.1700
Data Index: 6832273 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2519. Min Range: -5.2519
Max Act: 5.0957. Min Act: -0.1700
Data Index: 1526249 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2519. Min Range: -5.2519
Max Act: 5.0644. Min Act: -0.1700
Data Index: 7185211 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2519. Min Range: -5.2519
Max Act: 5.0644. Min Act: -0.1700
Data Index: 1114796 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #19