Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 684 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.3139. Min Range: -4.3139
Max Act: 4.3139. Min Act: -0.1700
Data Index: 5686498 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3139. Min Range: -4.3139
Max Act: 4.2826. Min Act: -0.1700
Data Index: 3017100 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3139. Min Range: -4.3139
Max Act: 4.2201. Min Act: -0.1700
Data Index: 4189301 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3139. Min Range: -4.3139
Max Act: 4.2201. Min Act: -0.1700
Data Index: 1556927 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3139. Min Range: -4.3139
Max Act: 4.2201. Min Act: -0.1700
Data Index: 3205454 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3139. Min Range: -4.3139
Max Act: 4.2201. Min Act: -0.1700
Data Index: 7437850 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3139. Min Range: -4.3139
Max Act: 4.1888. Min Act: -0.1700
Data Index: 7963487 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3139. Min Range: -4.3139
Max Act: 4.1888. Min Act: -0.1700
Data Index: 7297915 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3139. Min Range: -4.3139
Max Act: 4.1888. Min Act: -0.1700
Data Index: 274096 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3139. Min Range: -4.3139
Max Act: 4.1888. Min Act: -0.1700
Data Index: 7430095 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3139. Min Range: -4.3139
Max Act: 4.1576. Min Act: -0.1700
Data Index: 6682774 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3139. Min Range: -4.3139
Max Act: 4.1576. Min Act: -0.1700
Data Index: 2776452 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3139. Min Range: -4.3139
Max Act: 4.1576. Min Act: -0.1700
Data Index: 1623935 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3139. Min Range: -4.3139
Max Act: 4.1263. Min Act: -0.1700
Data Index: 5552150 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3139. Min Range: -4.3139
Max Act: 4.0951. Min Act: -0.1700
Data Index: 183498 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3139. Min Range: -4.3139
Max Act: 4.1263. Min Act: -0.1700
Data Index: 4779868 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3139. Min Range: -4.3139
Max Act: 4.0951. Min Act: -0.1700
Data Index: 7383771 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3139. Min Range: -4.3139
Max Act: 4.0951. Min Act: -0.1700
Data Index: 3880606 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3139. Min Range: -4.3139
Max Act: 4.1263. Min Act: -0.1700
Data Index: 3092616 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3139. Min Range: -4.3139
Max Act: 4.1263. Min Act: -0.1700
Data Index: 3202728 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #19