Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4726 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0294. Min Range: -4.0294
Max Act: 4.0294. Min Act: -0.1700
Data Index: 5060019 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0294. Min Range: -4.0294
Max Act: 3.9043. Min Act: -0.1700
Data Index: 3930720 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0294. Min Range: -4.0294
Max Act: 3.9043. Min Act: -0.1700
Data Index: 8159135 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0294. Min Range: -4.0294
Max Act: 3.8261. Min Act: -0.1700
Data Index: 3344728 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0294. Min Range: -4.0294
Max Act: 3.7949. Min Act: -0.1700
Data Index: 1203258 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0294. Min Range: -4.0294
Max Act: 3.7636. Min Act: -0.1700
Data Index: 1203274 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0294. Min Range: -4.0294
Max Act: 3.7636. Min Act: -0.1700
Data Index: 47298 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0294. Min Range: -4.0294
Max Act: 3.7167. Min Act: -0.1700
Data Index: 6397125 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0294. Min Range: -4.0294
Max Act: 3.7010. Min Act: -0.1700
Data Index: 963393 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0294. Min Range: -4.0294
Max Act: 3.6854. Min Act: -0.1700
Data Index: 2304854 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0294. Min Range: -4.0294
Max Act: 3.6854. Min Act: -0.1700
Data Index: 5081183 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0294. Min Range: -4.0294
Max Act: 3.6384. Min Act: -0.1700
Data Index: 575607 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0294. Min Range: -4.0294
Max Act: 3.6228. Min Act: -0.1700
Data Index: 1203278 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0294. Min Range: -4.0294
Max Act: 3.5758. Min Act: -0.1700
Data Index: 1203268 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0294. Min Range: -4.0294
Max Act: 3.5758. Min Act: -0.1700
Data Index: 2749161 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0294. Min Range: -4.0294
Max Act: 3.5915. Min Act: -0.1700
Data Index: 1203266 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0294. Min Range: -4.0294
Max Act: 3.5445. Min Act: -0.1700
Data Index: 3905229 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0294. Min Range: -4.0294
Max Act: 3.5289. Min Act: -0.1700
Data Index: 416783 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0294. Min Range: -4.0294
Max Act: 3.5132. Min Act: -0.1700
Data Index: 8055397 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0294. Min Range: -4.0294
Max Act: 3.4975. Min Act: -0.1700
Data Index: 1203264 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #19