Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5606 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0699. Min Range: -5.0699
Max Act: 5.0699. Min Act: -0.1700
Data Index: 1040099 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0699. Min Range: -5.0699
Max Act: 5.0386. Min Act: -0.1698
Data Index: 7131415 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0699. Min Range: -5.0699
Max Act: 4.9761. Min Act: -0.1700
Data Index: 2701550 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0699. Min Range: -5.0699
Max Act: 4.9449. Min Act: -0.1700
Data Index: 6990953 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0699. Min Range: -5.0699
Max Act: 4.9136. Min Act: -0.1700
Data Index: 212091 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0699. Min Range: -5.0699
Max Act: 4.9136. Min Act: -0.1700
Data Index: 2129998 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0699. Min Range: -5.0699
Max Act: 4.9136. Min Act: -0.1700
Data Index: 6902576 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0699. Min Range: -5.0699
Max Act: 4.9136. Min Act: -0.1699
Data Index: 7145929 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0699. Min Range: -5.0699
Max Act: 4.8824. Min Act: -0.1699
Data Index: 2337983 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0699. Min Range: -5.0699
Max Act: 4.8824. Min Act: -0.1700
Data Index: 549221 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0699. Min Range: -5.0699
Max Act: 4.8511. Min Act: -0.1700
Data Index: 4686776 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0699. Min Range: -5.0699
Max Act: 4.8824. Min Act: -0.1700
Data Index: 1953995 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0699. Min Range: -5.0699
Max Act: 4.8824. Min Act: -0.1700
Data Index: 5683200 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0699. Min Range: -5.0699
Max Act: 4.8824. Min Act: -0.1700
Data Index: 4544061 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0699. Min Range: -5.0699
Max Act: 4.8824. Min Act: -0.1700
Data Index: 4175222 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0699. Min Range: -5.0699
Max Act: 4.8511. Min Act: -0.1700
Data Index: 2750279 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0699. Min Range: -5.0699
Max Act: 4.8511. Min Act: -0.1700
Data Index: 6482697 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0699. Min Range: -5.0699
Max Act: 4.8511. Min Act: -0.1699
Data Index: 5058465 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0699. Min Range: -5.0699
Max Act: 4.8511. Min Act: -0.1698
Data Index: 3815964 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0699. Min Range: -5.0699
Max Act: 4.8511. Min Act: -0.1700
Data Index: 4853283 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #19