Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3380 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8366. Min Range: -5.8366
Max Act: 5.8366. Min Act: -0.1700
Data Index: 6484535 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8366. Min Range: -5.8366
Max Act: 5.7429. Min Act: -0.1700
Data Index: 6223322 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8366. Min Range: -5.8366
Max Act: 5.6804. Min Act: -0.1700
Data Index: 5204438 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8366. Min Range: -5.8366
Max Act: 5.6491. Min Act: -0.1700
Data Index: 5839890 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8366. Min Range: -5.8366
Max Act: 5.6179. Min Act: -0.1700
Data Index: 4818552 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8366. Min Range: -5.8366
Max Act: 5.6179. Min Act: -0.1700
Data Index: 2150079 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8366. Min Range: -5.8366
Max Act: 5.5866. Min Act: -0.1700
Data Index: 4830894 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8366. Min Range: -5.8366
Max Act: 5.5554. Min Act: -0.1700
Data Index: 3151842 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8366. Min Range: -5.8366
Max Act: 5.4616. Min Act: -0.1700
Data Index: 8333956 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8366. Min Range: -5.8366
Max Act: 5.4929. Min Act: -0.1700
Data Index: 5706849 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8366. Min Range: -5.8366
Max Act: 5.4616. Min Act: -0.1700
Data Index: 3283521 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8366. Min Range: -5.8366
Max Act: 5.4304. Min Act: -0.1700
Data Index: 5009765 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8366. Min Range: -5.8366
Max Act: 5.3991. Min Act: -0.1700
Data Index: 7053939 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8366. Min Range: -5.8366
Max Act: 5.3679. Min Act: -0.1700
Data Index: 5706573 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8366. Min Range: -5.8366
Max Act: 5.3679. Min Act: -0.1700
Data Index: 5478900 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8366. Min Range: -5.8366
Max Act: 5.3366. Min Act: -0.1700
Data Index: 810838 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8366. Min Range: -5.8366
Max Act: 5.3366. Min Act: -0.1700
Data Index: 5000352 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8366. Min Range: -5.8366
Max Act: 5.3366. Min Act: -0.1700
Data Index: 988515 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8366. Min Range: -5.8366
Max Act: 5.3679. Min Act: -0.1700
Data Index: 1080138 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8366. Min Range: -5.8366
Max Act: 5.3054. Min Act: -0.1700
Data Index: 2470186 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #19