Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3354 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9865. Min Range: -4.9865
Max Act: 4.9865. Min Act: -0.1700
Data Index: 5766271 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9865. Min Range: -4.9865
Max Act: 4.9553. Min Act: -0.1700
Data Index: 4321078 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9865. Min Range: -4.9865
Max Act: 4.7365. Min Act: -0.1700
Data Index: 201313 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9865. Min Range: -4.9865
Max Act: 4.7053. Min Act: -0.1700
Data Index: 788473 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9865. Min Range: -4.9865
Max Act: 4.7053. Min Act: -0.1700
Data Index: 3182880 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9865. Min Range: -4.9865
Max Act: 4.6740. Min Act: -0.1700
Data Index: 5804504 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9865. Min Range: -4.9865
Max Act: 4.6740. Min Act: -0.1700
Data Index: 6576050 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9865. Min Range: -4.9865
Max Act: 4.6740. Min Act: -0.1700
Data Index: 8306655 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9865. Min Range: -4.9865
Max Act: 4.6428. Min Act: -0.1700
Data Index: 1126520 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9865. Min Range: -4.9865
Max Act: 4.6115. Min Act: -0.1700
Data Index: 7973185 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9865. Min Range: -4.9865
Max Act: 4.6115. Min Act: -0.1700
Data Index: 4203375 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9865. Min Range: -4.9865
Max Act: 4.6115. Min Act: -0.1700
Data Index: 7417620 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9865. Min Range: -4.9865
Max Act: 4.6115. Min Act: -0.1700
Data Index: 4775979 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9865. Min Range: -4.9865
Max Act: 4.6115. Min Act: -0.1700
Data Index: 6294122 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9865. Min Range: -4.9865
Max Act: 4.5803. Min Act: -0.1700
Data Index: 881822 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9865. Min Range: -4.9865
Max Act: 4.6115. Min Act: -0.1700
Data Index: 1479680 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9865. Min Range: -4.9865
Max Act: 4.5803. Min Act: -0.1700
Data Index: 1593642 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9865. Min Range: -4.9865
Max Act: 4.5803. Min Act: -0.1700
Data Index: 5170668 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9865. Min Range: -4.9865
Max Act: 4.5803. Min Act: -0.1700
Data Index: 3983725 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9865. Min Range: -4.9865
Max Act: 4.5803. Min Act: -0.1700
Data Index: 5542315 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #19