Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3513 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9758. Min Range: -5.9758
Max Act: 5.9758. Min Act: -0.1700
Data Index: 1142613 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9758. Min Range: -5.9758
Max Act: 5.7258. Min Act: -0.1700
Data Index: 4770549 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9758. Min Range: -5.9758
Max Act: 5.6633. Min Act: -0.1700
Data Index: 4080000 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9758. Min Range: -5.9758
Max Act: 5.6320. Min Act: -0.1700
Data Index: 4745256 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9758. Min Range: -5.9758
Max Act: 5.6008. Min Act: -0.1700
Data Index: 6344733 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9758. Min Range: -5.9758
Max Act: 5.6008. Min Act: -0.1700
Data Index: 4709884 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9758. Min Range: -5.9758
Max Act: 5.5695. Min Act: -0.1700
Data Index: 2656911 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9758. Min Range: -5.9758
Max Act: 5.5383. Min Act: -0.1700
Data Index: 949092 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9758. Min Range: -5.9758
Max Act: 5.5383. Min Act: -0.1700
Data Index: 1644136 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9758. Min Range: -5.9758
Max Act: 5.5383. Min Act: -0.1700
Data Index: 2778507 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9758. Min Range: -5.9758
Max Act: 5.5070. Min Act: -0.1700
Data Index: 2222982 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9758. Min Range: -5.9758
Max Act: 5.5070. Min Act: -0.1700
Data Index: 8670553 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9758. Min Range: -5.9758
Max Act: 5.5070. Min Act: -0.1700
Data Index: 3812195 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9758. Min Range: -5.9758
Max Act: 5.4445. Min Act: -0.1700
Data Index: 2640182 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9758. Min Range: -5.9758
Max Act: 5.4445. Min Act: -0.1700
Data Index: 4204072 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9758. Min Range: -5.9758
Max Act: 5.4133. Min Act: -0.1700
Data Index: 7017717 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9758. Min Range: -5.9758
Max Act: 5.3820. Min Act: -0.1700
Data Index: 2634939 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9758. Min Range: -5.9758
Max Act: 5.3508. Min Act: -0.1700
Data Index: 7818902 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9758. Min Range: -5.9758
Max Act: 5.3508. Min Act: -0.1700
Data Index: 156441 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9758. Min Range: -5.9758
Max Act: 5.3508. Min Act: -0.1700
Data Index: 7029387 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #19