Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3312 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.2212. Min Range: -3.2212
Max Act: 3.2212. Min Act: -0.1700
Data Index: 29472 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2212. Min Range: -3.2212
Max Act: 2.9532. Min Act: -0.1700
Data Index: 7282295 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2212. Min Range: -3.2212
Max Act: 2.8898. Min Act: -0.1700
Data Index: 3378710 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2212. Min Range: -3.2212
Max Act: 2.8580. Min Act: -0.1700
Data Index: 1647840 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2212. Min Range: -3.2212
Max Act: 2.8580. Min Act: -0.1700
Data Index: 3002744 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2212. Min Range: -3.2212
Max Act: 2.8580. Min Act: -0.1700
Data Index: 8739096 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2212. Min Range: -3.2212
Max Act: 2.8421. Min Act: -0.1700
Data Index: 4751925 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2212. Min Range: -3.2212
Max Act: 2.8421. Min Act: -0.1700
Data Index: 1479207 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2212. Min Range: -3.2212
Max Act: 2.8580. Min Act: -0.1700
Data Index: 5652249 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2212. Min Range: -3.2212
Max Act: 2.8739. Min Act: -0.1700
Data Index: 4362627 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2212. Min Range: -3.2212
Max Act: 2.8421. Min Act: -0.1700
Data Index: 1100958 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2212. Min Range: -3.2212
Max Act: 2.8580. Min Act: -0.1700
Data Index: 5380405 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2212. Min Range: -3.2212
Max Act: 2.8580. Min Act: -0.1700
Data Index: 2576713 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2212. Min Range: -3.2212
Max Act: 2.8421. Min Act: -0.1700
Data Index: 7602974 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2212. Min Range: -3.2212
Max Act: 2.8421. Min Act: -0.1700
Data Index: 7355701 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2212. Min Range: -3.2212
Max Act: 2.8421. Min Act: -0.1700
Data Index: 1563981 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2212. Min Range: -3.2212
Max Act: 2.8421. Min Act: -0.1700
Data Index: 3968329 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2212. Min Range: -3.2212
Max Act: 2.8262. Min Act: -0.1700
Data Index: 3008052 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2212. Min Range: -3.2212
Max Act: 2.8262. Min Act: -0.1700
Data Index: 2500474 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2212. Min Range: -3.2212
Max Act: 2.8103. Min Act: -0.1700
Data Index: 4224511 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #19