Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5303 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.6072. Min Range: -1.6072
Max Act: 1.6072. Min Act: -0.1700
Data Index: 6537493 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.6072. Min Range: -1.6072
Max Act: 1.6072. Min Act: -0.1700
Data Index: 6686308 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.6072. Min Range: -1.6072
Max Act: 1.4846. Min Act: -0.1700
Data Index: 5557466 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.6072. Min Range: -1.6072
Max Act: 1.4670. Min Act: -0.1700
Data Index: 2201793 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.6072. Min Range: -1.6072
Max Act: 1.4670. Min Act: -0.1700
Data Index: 335592 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.6072. Min Range: -1.6072
Max Act: 1.4670. Min Act: -0.1700
Data Index: 2596410 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.6072. Min Range: -1.6072
Max Act: 1.4670. Min Act: -0.1700
Data Index: 3974118 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.6072. Min Range: -1.6072
Max Act: 1.4494. Min Act: -0.1700
Data Index: 934374 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.6072. Min Range: -1.6072
Max Act: 1.4318. Min Act: -0.1700
Data Index: 3237029 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.6072. Min Range: -1.6072
Max Act: 1.4318. Min Act: -0.1700
Data Index: 4664138 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.6072. Min Range: -1.6072
Max Act: 1.4318. Min Act: -0.1700
Data Index: 3793264 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.6072. Min Range: -1.6072
Max Act: 1.4318. Min Act: -0.1700
Data Index: 8367985 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.6072. Min Range: -1.6072
Max Act: 1.3966. Min Act: -0.1700
Data Index: 167974 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.6072. Min Range: -1.6072
Max Act: 1.3966. Min Act: -0.1700
Data Index: 6314176 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.6072. Min Range: -1.6072
Max Act: 1.3966. Min Act: -0.1700
Data Index: 6054278 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.6072. Min Range: -1.6072
Max Act: 1.4142. Min Act: -0.1700
Data Index: 7067358 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.6072. Min Range: -1.6072
Max Act: 1.3966. Min Act: -0.1700
Data Index: 6592274 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.6072. Min Range: -1.6072
Max Act: 1.3966. Min Act: -0.1700
Data Index: 167977 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.6072. Min Range: -1.6072
Max Act: 1.3966. Min Act: -0.1700
Data Index: 2570912 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.6072. Min Range: -1.6072
Max Act: 1.3966. Min Act: -0.1700
Data Index: 6075306 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #19