Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3144 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7760. Min Range: -7.7760
Max Act: 7.7760. Min Act: -0.1700
Data Index: 8330288 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7760. Min Range: -7.7760
Max Act: 7.5885. Min Act: -0.1700
Data Index: 5404366 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7760. Min Range: -7.7760
Max Act: 7.5260. Min Act: -0.1700
Data Index: 2566183 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7760. Min Range: -7.7760
Max Act: 7.2760. Min Act: -0.1700
Data Index: 8282657 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7760. Min Range: -7.7760
Max Act: 7.1822. Min Act: -0.1700
Data Index: 6101554 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7760. Min Range: -7.7760
Max Act: 7.1510. Min Act: -0.1700
Data Index: 3459 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7760. Min Range: -7.7760
Max Act: 7.0885. Min Act: -0.1700
Data Index: 2573664 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7760. Min Range: -7.7760
Max Act: 7.0885. Min Act: -0.1700
Data Index: 7918057 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7760. Min Range: -7.7760
Max Act: 7.0885. Min Act: -0.1700
Data Index: 756407 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7760. Min Range: -7.7760
Max Act: 7.0885. Min Act: -0.1700
Data Index: 2390892 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7760. Min Range: -7.7760
Max Act: 7.0572. Min Act: -0.1700
Data Index: 5779905 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7760. Min Range: -7.7760
Max Act: 7.0572. Min Act: -0.1700
Data Index: 4080828 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7760. Min Range: -7.7760
Max Act: 7.0572. Min Act: -0.1700
Data Index: 6256696 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7760. Min Range: -7.7760
Max Act: 7.0885. Min Act: -0.1700
Data Index: 2669487 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7760. Min Range: -7.7760
Max Act: 6.9947. Min Act: -0.1700
Data Index: 8463588 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7760. Min Range: -7.7760
Max Act: 7.0260. Min Act: -0.1700
Data Index: 2778722 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7760. Min Range: -7.7760
Max Act: 7.0260. Min Act: -0.1700
Data Index: 5330212 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7760. Min Range: -7.7760
Max Act: 7.0260. Min Act: -0.1700
Data Index: 3766322 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7760. Min Range: -7.7760
Max Act: 7.0260. Min Act: -0.1700
Data Index: 8478541 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7760. Min Range: -7.7760
Max Act: 6.9947. Min Act: -0.1700
Data Index: 5385466 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19