Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2155 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2194. Min Range: -8.2194
Max Act: 8.2194. Min Act: -0.1700
Data Index: 8374936 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2194. Min Range: -8.2194
Max Act: 8.1569. Min Act: -0.1700
Data Index: 4064561 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2194. Min Range: -8.2194
Max Act: 8.0006. Min Act: -0.1700
Data Index: 3069662 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2194. Min Range: -8.2194
Max Act: 7.8756. Min Act: -0.1700
Data Index: 8442509 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2194. Min Range: -8.2194
Max Act: 7.8756. Min Act: -0.1700
Data Index: 8152200 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2194. Min Range: -8.2194
Max Act: 7.8444. Min Act: -0.1700
Data Index: 4203677 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2194. Min Range: -8.2194
Max Act: 7.8131. Min Act: -0.1700
Data Index: 8102932 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2194. Min Range: -8.2194
Max Act: 7.8131. Min Act: -0.1700
Data Index: 1378535 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2194. Min Range: -8.2194
Max Act: 7.7819. Min Act: -0.1700
Data Index: 797173 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2194. Min Range: -8.2194
Max Act: 7.7819. Min Act: -0.1700
Data Index: 6113601 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2194. Min Range: -8.2194
Max Act: 7.7506. Min Act: -0.1700
Data Index: 7984751 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2194. Min Range: -8.2194
Max Act: 7.7506. Min Act: -0.1700
Data Index: 7261884 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2194. Min Range: -8.2194
Max Act: 7.6881. Min Act: -0.1700
Data Index: 3793129 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2194. Min Range: -8.2194
Max Act: 7.6256. Min Act: -0.1700
Data Index: 7020380 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2194. Min Range: -8.2194
Max Act: 7.6569. Min Act: -0.1700
Data Index: 5689723 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2194. Min Range: -8.2194
Max Act: 7.5944. Min Act: -0.1700
Data Index: 1360941 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2194. Min Range: -8.2194
Max Act: 7.5944. Min Act: -0.1700
Data Index: 7422461 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2194. Min Range: -8.2194
Max Act: 7.5631. Min Act: -0.1700
Data Index: 6253641 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2194. Min Range: -8.2194
Max Act: 7.5944. Min Act: -0.1700
Data Index: 4051429 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2194. Min Range: -8.2194
Max Act: 7.5631. Min Act: -0.1700
Data Index: 6438701 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #19