Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2756 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4194. Min Range: -5.4194
Max Act: 5.4194. Min Act: -0.1700
Data Index: 7580778 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4194. Min Range: -5.4194
Max Act: 5.4194. Min Act: -0.1700
Data Index: 8016265 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4194. Min Range: -5.4194
Max Act: 5.3881. Min Act: -0.1700
Data Index: 2186616 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4194. Min Range: -5.4194
Max Act: 5.3881. Min Act: -0.1700
Data Index: 7200898 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4194. Min Range: -5.4194
Max Act: 5.3569. Min Act: -0.1700
Data Index: 6759249 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4194. Min Range: -5.4194
Max Act: 5.3256. Min Act: -0.1700
Data Index: 7430558 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4194. Min Range: -5.4194
Max Act: 5.3256. Min Act: -0.1700
Data Index: 4297670 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4194. Min Range: -5.4194
Max Act: 5.3569. Min Act: -0.1700
Data Index: 5171718 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4194. Min Range: -5.4194
Max Act: 5.3256. Min Act: -0.1700
Data Index: 6370290 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4194. Min Range: -5.4194
Max Act: 5.2944. Min Act: -0.1700
Data Index: 1500304 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4194. Min Range: -5.4194
Max Act: 5.2944. Min Act: -0.1700
Data Index: 6109852 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4194. Min Range: -5.4194
Max Act: 5.2944. Min Act: -0.1700
Data Index: 6287437 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4194. Min Range: -5.4194
Max Act: 5.2944. Min Act: -0.1700
Data Index: 7322015 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4194. Min Range: -5.4194
Max Act: 5.2944. Min Act: -0.1700
Data Index: 6313201 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4194. Min Range: -5.4194
Max Act: 5.2319. Min Act: -0.1700
Data Index: 132013 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4194. Min Range: -5.4194
Max Act: 5.2631. Min Act: -0.1700
Data Index: 1788647 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4194. Min Range: -5.4194
Max Act: 5.2319. Min Act: -0.1700
Data Index: 7070713 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4194. Min Range: -5.4194
Max Act: 5.2631. Min Act: -0.1700
Data Index: 1704548 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4194. Min Range: -5.4194
Max Act: 5.2631. Min Act: -0.1700
Data Index: 676395 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4194. Min Range: -5.4194
Max Act: 5.2319. Min Act: -0.1700
Data Index: 2327546 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #19