Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2983 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1197. Min Range: -5.1197
Max Act: 5.1197. Min Act: -0.1700
Data Index: 1500274 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1197. Min Range: -5.1197
Max Act: 5.0572. Min Act: -0.1700
Data Index: 5490214 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1197. Min Range: -5.1197
Max Act: 5.0572. Min Act: -0.1700
Data Index: 7260117 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1197. Min Range: -5.1197
Max Act: 4.9947. Min Act: -0.1700
Data Index: 280757 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1197. Min Range: -5.1197
Max Act: 5.0259. Min Act: -0.1700
Data Index: 6799467 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1197. Min Range: -5.1197
Max Act: 5.0259. Min Act: -0.1700
Data Index: 3415308 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1197. Min Range: -5.1197
Max Act: 5.0259. Min Act: -0.1700
Data Index: 7294298 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1197. Min Range: -5.1197
Max Act: 4.9947. Min Act: -0.1700
Data Index: 5156661 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1197. Min Range: -5.1197
Max Act: 4.9947. Min Act: -0.1700
Data Index: 3972693 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1197. Min Range: -5.1197
Max Act: 4.9634. Min Act: -0.1700
Data Index: 6502226 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1197. Min Range: -5.1197
Max Act: 4.9634. Min Act: -0.1700
Data Index: 986267 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1197. Min Range: -5.1197
Max Act: 4.9634. Min Act: -0.1700
Data Index: 2243859 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1197. Min Range: -5.1197
Max Act: 4.9322. Min Act: -0.1700
Data Index: 3547244 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1197. Min Range: -5.1197
Max Act: 4.9322. Min Act: -0.1700
Data Index: 3537465 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1197. Min Range: -5.1197
Max Act: 4.9322. Min Act: -0.1700
Data Index: 5787373 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1197. Min Range: -5.1197
Max Act: 4.9009. Min Act: -0.1700
Data Index: 85082 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1197. Min Range: -5.1197
Max Act: 4.9009. Min Act: -0.1700
Data Index: 1852404 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1197. Min Range: -5.1197
Max Act: 4.9009. Min Act: -0.1700
Data Index: 2682122 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1197. Min Range: -5.1197
Max Act: 4.9009. Min Act: -0.1700
Data Index: 6597051 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1197. Min Range: -5.1197
Max Act: 4.8697. Min Act: -0.1700
Data Index: 2262448 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #19