Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5846 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0510. Min Range: -6.0510
Max Act: 6.0510. Min Act: -0.1700
Data Index: 1448091 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0510. Min Range: -6.0510
Max Act: 5.9885. Min Act: -0.1700
Data Index: 7565199 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0510. Min Range: -6.0510
Max Act: 5.9260. Min Act: -0.1700
Data Index: 1629396 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0510. Min Range: -6.0510
Max Act: 5.8010. Min Act: -0.1700
Data Index: 2495226 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0510. Min Range: -6.0510
Max Act: 5.8010. Min Act: -0.1700
Data Index: 8602365 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0510. Min Range: -6.0510
Max Act: 5.6760. Min Act: -0.1700
Data Index: 5258858 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0510. Min Range: -6.0510
Max Act: 5.6760. Min Act: -0.1700
Data Index: 447713 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0510. Min Range: -6.0510
Max Act: 5.6760. Min Act: -0.1700
Data Index: 6691201 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0510. Min Range: -6.0510
Max Act: 5.6448. Min Act: -0.1700
Data Index: 3815210 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0510. Min Range: -6.0510
Max Act: 5.6135. Min Act: -0.1700
Data Index: 314342 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0510. Min Range: -6.0510
Max Act: 5.6135. Min Act: -0.1700
Data Index: 5829972 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0510. Min Range: -6.0510
Max Act: 5.6135. Min Act: -0.1700
Data Index: 352093 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0510. Min Range: -6.0510
Max Act: 5.5823. Min Act: -0.1700
Data Index: 2049038 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0510. Min Range: -6.0510
Max Act: 5.5510. Min Act: -0.1700
Data Index: 8251924 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0510. Min Range: -6.0510
Max Act: 5.5198. Min Act: -0.1700
Data Index: 8460871 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0510. Min Range: -6.0510
Max Act: 5.4885. Min Act: -0.1700
Data Index: 8077803 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0510. Min Range: -6.0510
Max Act: 5.4573. Min Act: -0.1700
Data Index: 4105177 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0510. Min Range: -6.0510
Max Act: 5.4573. Min Act: -0.1700
Data Index: 2311502 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0510. Min Range: -6.0510
Max Act: 5.4260. Min Act: -0.1700
Data Index: 2732142 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0510. Min Range: -6.0510
Max Act: 5.4260. Min Act: -0.1700
Data Index: 3764050 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #19