Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 271 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5374. Min Range: -6.5374
Max Act: 6.5374. Min Act: -0.1700
Data Index: 3753615 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5374. Min Range: -6.5374
Max Act: 6.3499. Min Act: -0.1700
Data Index: 8163733 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5374. Min Range: -6.5374
Max Act: 6.2874. Min Act: -0.1700
Data Index: 6400032 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5374. Min Range: -6.5374
Max Act: 6.2249. Min Act: -0.1700
Data Index: 6227461 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5374. Min Range: -6.5374
Max Act: 6.1312. Min Act: -0.1700
Data Index: 5403910 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5374. Min Range: -6.5374
Max Act: 6.0374. Min Act: -0.1700
Data Index: 4300974 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5374. Min Range: -6.5374
Max Act: 6.0062. Min Act: -0.1700
Data Index: 531430 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5374. Min Range: -6.5374
Max Act: 5.9749. Min Act: -0.1700
Data Index: 4126483 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5374. Min Range: -6.5374
Max Act: 5.9749. Min Act: -0.1700
Data Index: 1331173 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5374. Min Range: -6.5374
Max Act: 5.9437. Min Act: -0.1700
Data Index: 3667351 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5374. Min Range: -6.5374
Max Act: 5.9437. Min Act: -0.1700
Data Index: 5407974 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5374. Min Range: -6.5374
Max Act: 5.9124. Min Act: -0.1700
Data Index: 942650 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5374. Min Range: -6.5374
Max Act: 5.9124. Min Act: -0.1700
Data Index: 7011414 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5374. Min Range: -6.5374
Max Act: 5.9124. Min Act: -0.1700
Data Index: 7419012 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5374. Min Range: -6.5374
Max Act: 5.9124. Min Act: -0.1700
Data Index: 2350386 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5374. Min Range: -6.5374
Max Act: 5.9124. Min Act: -0.1700
Data Index: 759638 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5374. Min Range: -6.5374
Max Act: 5.8812. Min Act: -0.1700
Data Index: 6499957 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5374. Min Range: -6.5374
Max Act: 5.9124. Min Act: -0.1700
Data Index: 3012932 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5374. Min Range: -6.5374
Max Act: 5.8812. Min Act: -0.1700
Data Index: 1646108 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5374. Min Range: -6.5374
Max Act: 5.8812. Min Act: -0.1700
Data Index: 6642768 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #19