Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3578 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4841. Min Range: -7.4841
Max Act: 7.4841. Min Act: -0.1700
Data Index: 2720177 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4841. Min Range: -7.4841
Max Act: 7.2966. Min Act: -0.1700
Data Index: 2190334 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4841. Min Range: -7.4841
Max Act: 7.2966. Min Act: -0.1700
Data Index: 3028936 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4841. Min Range: -7.4841
Max Act: 7.2653. Min Act: -0.1700
Data Index: 2317102 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4841. Min Range: -7.4841
Max Act: 7.2653. Min Act: -0.1700
Data Index: 6225187 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4841. Min Range: -7.4841
Max Act: 7.2653. Min Act: -0.1700
Data Index: 2206817 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4841. Min Range: -7.4841
Max Act: 7.2341. Min Act: -0.1700
Data Index: 6294131 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4841. Min Range: -7.4841
Max Act: 7.2341. Min Act: -0.1700
Data Index: 3770229 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4841. Min Range: -7.4841
Max Act: 7.2028. Min Act: -0.1700
Data Index: 7388294 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4841. Min Range: -7.4841
Max Act: 7.1716. Min Act: -0.1700
Data Index: 5432889 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4841. Min Range: -7.4841
Max Act: 7.2028. Min Act: -0.1700
Data Index: 6318561 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4841. Min Range: -7.4841
Max Act: 7.1403. Min Act: -0.1700
Data Index: 4736213 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4841. Min Range: -7.4841
Max Act: 7.1091. Min Act: -0.1700
Data Index: 4678363 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4841. Min Range: -7.4841
Max Act: 7.0778. Min Act: -0.1700
Data Index: 1616356 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4841. Min Range: -7.4841
Max Act: 7.0778. Min Act: -0.1700
Data Index: 4647846 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4841. Min Range: -7.4841
Max Act: 7.0778. Min Act: -0.1700
Data Index: 6726001 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4841. Min Range: -7.4841
Max Act: 7.0153. Min Act: -0.1700
Data Index: 1751438 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4841. Min Range: -7.4841
Max Act: 7.0153. Min Act: -0.1700
Data Index: 534972 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4841. Min Range: -7.4841
Max Act: 6.9841. Min Act: -0.1700
Data Index: 8822381 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4841. Min Range: -7.4841
Max Act: 6.9841. Min Act: -0.1700
Data Index: 5481705 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #19