Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5663 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3643. Min Range: -8.3643
Max Act: 8.3643. Min Act: -0.1700
Data Index: 1831567 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3643. Min Range: -8.3643
Max Act: 8.3018. Min Act: -0.1700
Data Index: 4642184 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3643. Min Range: -8.3643
Max Act: 8.3643. Min Act: -0.1700
Data Index: 8292439 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3643. Min Range: -8.3643
Max Act: 8.2393. Min Act: -0.1700
Data Index: 2373744 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3643. Min Range: -8.3643
Max Act: 8.2393. Min Act: -0.1700
Data Index: 5805261 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3643. Min Range: -8.3643
Max Act: 8.2393. Min Act: -0.1700
Data Index: 2852108 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3643. Min Range: -8.3643
Max Act: 8.2393. Min Act: -0.1700
Data Index: 7148856 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3643. Min Range: -8.3643
Max Act: 8.2393. Min Act: -0.1700
Data Index: 2684128 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3643. Min Range: -8.3643
Max Act: 8.1768. Min Act: -0.1700
Data Index: 884133 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3643. Min Range: -8.3643
Max Act: 8.1768. Min Act: -0.1700
Data Index: 877520 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3643. Min Range: -8.3643
Max Act: 8.1143. Min Act: -0.1700
Data Index: 5040266 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3643. Min Range: -8.3643
Max Act: 8.1143. Min Act: -0.1700
Data Index: 5545545 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3643. Min Range: -8.3643
Max Act: 8.1143. Min Act: -0.1700
Data Index: 3593150 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3643. Min Range: -8.3643
Max Act: 8.1143. Min Act: -0.1700
Data Index: 6777817 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3643. Min Range: -8.3643
Max Act: 8.1143. Min Act: -0.1700
Data Index: 3142897 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3643. Min Range: -8.3643
Max Act: 8.1143. Min Act: -0.1700
Data Index: 6025832 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3643. Min Range: -8.3643
Max Act: 8.1143. Min Act: -0.1700
Data Index: 6318390 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3643. Min Range: -8.3643
Max Act: 8.1143. Min Act: -0.1700
Data Index: 1175991 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3643. Min Range: -8.3643
Max Act: 8.1143. Min Act: -0.1700
Data Index: 2827364 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3643. Min Range: -8.3643
Max Act: 8.0518. Min Act: -0.1700
Data Index: 361500 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #19