Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1646 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0400. Min Range: -6.0400
Max Act: 6.0400. Min Act: -0.1700
Data Index: 8277838 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0400. Min Range: -6.0400
Max Act: 5.8213. Min Act: -0.1700
Data Index: 4145210 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0400. Min Range: -6.0400
Max Act: 5.8213. Min Act: -0.1700
Data Index: 2995312 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0400. Min Range: -6.0400
Max Act: 5.8213. Min Act: -0.1700
Data Index: 236263 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0400. Min Range: -6.0400
Max Act: 5.7588. Min Act: -0.1700
Data Index: 3714170 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0400. Min Range: -6.0400
Max Act: 5.7900. Min Act: -0.1700
Data Index: 5111655 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0400. Min Range: -6.0400
Max Act: 5.7588. Min Act: -0.1700
Data Index: 8735997 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0400. Min Range: -6.0400
Max Act: 5.7275. Min Act: -0.1700
Data Index: 650263 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0400. Min Range: -6.0400
Max Act: 5.7275. Min Act: -0.1700
Data Index: 1695711 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0400. Min Range: -6.0400
Max Act: 5.7275. Min Act: -0.1700
Data Index: 8736000 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0400. Min Range: -6.0400
Max Act: 5.6963. Min Act: -0.1700
Data Index: 5250535 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0400. Min Range: -6.0400
Max Act: 5.6963. Min Act: -0.1700
Data Index: 6117587 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0400. Min Range: -6.0400
Max Act: 5.6650. Min Act: -0.1700
Data Index: 6655923 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0400. Min Range: -6.0400
Max Act: 5.6025. Min Act: -0.1700
Data Index: 4029184 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0400. Min Range: -6.0400
Max Act: 5.6025. Min Act: -0.1700
Data Index: 459039 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0400. Min Range: -6.0400
Max Act: 5.5713. Min Act: -0.1700
Data Index: 7052021 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0400. Min Range: -6.0400
Max Act: 5.5713. Min Act: -0.1700
Data Index: 2325400 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0400. Min Range: -6.0400
Max Act: 5.5400. Min Act: -0.1700
Data Index: 851922 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0400. Min Range: -6.0400
Max Act: 5.5713. Min Act: -0.1700
Data Index: 2429957 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0400. Min Range: -6.0400
Max Act: 5.5713. Min Act: -0.1700
Data Index: 7787771 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #19