Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2321 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4280. Min Range: -7.4280
Max Act: 7.4280. Min Act: -0.1700
Data Index: 6831946 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4280. Min Range: -7.4280
Max Act: 7.3655. Min Act: -0.1700
Data Index: 5481166 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4280. Min Range: -7.4280
Max Act: 7.3030. Min Act: -0.1700
Data Index: 6319729 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4280. Min Range: -7.4280
Max Act: 7.2405. Min Act: -0.1700
Data Index: 5815231 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4280. Min Range: -7.4280
Max Act: 7.0530. Min Act: -0.1700
Data Index: 8386724 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4280. Min Range: -7.4280
Max Act: 7.0530. Min Act: -0.1700
Data Index: 2206962 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4280. Min Range: -7.4280
Max Act: 6.9593. Min Act: -0.1700
Data Index: 522829 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4280. Min Range: -7.4280
Max Act: 6.9593. Min Act: -0.1700
Data Index: 4818050 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4280. Min Range: -7.4280
Max Act: 6.9280. Min Act: -0.1700
Data Index: 3194647 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4280. Min Range: -7.4280
Max Act: 6.9280. Min Act: -0.1700
Data Index: 8141076 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4280. Min Range: -7.4280
Max Act: 6.8655. Min Act: -0.1700
Data Index: 4077478 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4280. Min Range: -7.4280
Max Act: 6.8968. Min Act: -0.1700
Data Index: 7840761 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4280. Min Range: -7.4280
Max Act: 6.8343. Min Act: -0.1700
Data Index: 5948156 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4280. Min Range: -7.4280
Max Act: 6.8343. Min Act: -0.1700
Data Index: 8285316 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4280. Min Range: -7.4280
Max Act: 6.8343. Min Act: -0.1700
Data Index: 2565465 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4280. Min Range: -7.4280
Max Act: 6.8655. Min Act: -0.1700
Data Index: 7596241 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4280. Min Range: -7.4280
Max Act: 6.8030. Min Act: -0.1700
Data Index: 3243434 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4280. Min Range: -7.4280
Max Act: 6.7718. Min Act: -0.1700
Data Index: 5880469 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4280. Min Range: -7.4280
Max Act: 6.7718. Min Act: -0.1700
Data Index: 2626894 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4280. Min Range: -7.4280
Max Act: 6.7718. Min Act: -0.1700
Data Index: 6617137 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #19