Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2392 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.4899. Min Range: -3.4899
Max Act: 3.4899. Min Act: -0.1700
Data Index: 617148 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4899. Min Range: -3.4899
Max Act: 3.4272. Min Act: -0.1700
Data Index: 3616906 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4899. Min Range: -3.4899
Max Act: 3.4115. Min Act: -0.1700
Data Index: 7941084 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4899. Min Range: -3.4899
Max Act: 3.3959. Min Act: -0.1700
Data Index: 7109244 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4899. Min Range: -3.4899
Max Act: 3.3802. Min Act: -0.1700
Data Index: 4893710 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4899. Min Range: -3.4899
Max Act: 3.3802. Min Act: -0.1700
Data Index: 7406220 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4899. Min Range: -3.4899
Max Act: 3.3802. Min Act: -0.1700
Data Index: 6574999 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4899. Min Range: -3.4899
Max Act: 3.3488. Min Act: -0.1700
Data Index: 7195426 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4899. Min Range: -3.4899
Max Act: 3.3488. Min Act: -0.1700
Data Index: 7839789 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4899. Min Range: -3.4899
Max Act: 3.3331. Min Act: -0.1700
Data Index: 6810573 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4899. Min Range: -3.4899
Max Act: 3.3488. Min Act: -0.1700
Data Index: 8525664 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4899. Min Range: -3.4899
Max Act: 3.3331. Min Act: -0.1700
Data Index: 6062154 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4899. Min Range: -3.4899
Max Act: 3.3174. Min Act: -0.1700
Data Index: 5742186 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4899. Min Range: -3.4899
Max Act: 3.3174. Min Act: -0.1700
Data Index: 1715455 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4899. Min Range: -3.4899
Max Act: 3.3174. Min Act: -0.1700
Data Index: 8242304 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4899. Min Range: -3.4899
Max Act: 3.3017. Min Act: -0.1700
Data Index: 589072 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4899. Min Range: -3.4899
Max Act: 3.2860. Min Act: -0.1700
Data Index: 4809307 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4899. Min Range: -3.4899
Max Act: 3.2860. Min Act: -0.1700
Data Index: 8117203 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4899. Min Range: -3.4899
Max Act: 3.2703. Min Act: -0.1700
Data Index: 1446441 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4899. Min Range: -3.4899
Max Act: 3.2860. Min Act: -0.1700
Data Index: 440777 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #19