Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2802 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5220. Min Range: -7.5220
Max Act: 7.5220. Min Act: -0.1700
Data Index: 3355068 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5220. Min Range: -7.5220
Max Act: 7.4282. Min Act: -0.1700
Data Index: 1696241 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5220. Min Range: -7.5220
Max Act: 7.3032. Min Act: -0.1700
Data Index: 1214206 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5220. Min Range: -7.5220
Max Act: 7.0845. Min Act: -0.1700
Data Index: 1830328 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5220. Min Range: -7.5220
Max Act: 7.0845. Min Act: -0.1700
Data Index: 5873194 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5220. Min Range: -7.5220
Max Act: 6.9907. Min Act: -0.1700
Data Index: 1584864 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5220. Min Range: -7.5220
Max Act: 6.9282. Min Act: -0.1700
Data Index: 5987608 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5220. Min Range: -7.5220
Max Act: 6.8970. Min Act: -0.1700
Data Index: 8637516 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5220. Min Range: -7.5220
Max Act: 6.8657. Min Act: -0.1700
Data Index: 6691665 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5220. Min Range: -7.5220
Max Act: 6.8345. Min Act: -0.1700
Data Index: 8050484 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5220. Min Range: -7.5220
Max Act: 6.8345. Min Act: -0.1700
Data Index: 8129929 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5220. Min Range: -7.5220
Max Act: 6.8345. Min Act: -0.1700
Data Index: 459215 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5220. Min Range: -7.5220
Max Act: 6.8345. Min Act: -0.1700
Data Index: 6950622 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5220. Min Range: -7.5220
Max Act: 6.8032. Min Act: -0.1700
Data Index: 539587 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5220. Min Range: -7.5220
Max Act: 6.8032. Min Act: -0.1700
Data Index: 2024334 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5220. Min Range: -7.5220
Max Act: 6.7407. Min Act: -0.1700
Data Index: 7827437 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5220. Min Range: -7.5220
Max Act: 6.7407. Min Act: -0.1700
Data Index: 2669090 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5220. Min Range: -7.5220
Max Act: 6.7407. Min Act: -0.1700
Data Index: 1524296 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5220. Min Range: -7.5220
Max Act: 6.7095. Min Act: -0.1700
Data Index: 4239937 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5220. Min Range: -7.5220
Max Act: 6.6470. Min Act: -0.1700
Data Index: 5544705 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #19