Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5109 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.0821. Min Range: -10.0821
Max Act: 10.0821. Min Act: -0.1700
Data Index: 3600537 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.0821. Min Range: -10.0821
Max Act: 10.0821. Min Act: -0.1700
Data Index: 2072297 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.0821. Min Range: -10.0821
Max Act: 10.0821. Min Act: -0.1700
Data Index: 7951453 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.0821. Min Range: -10.0821
Max Act: 9.8946. Min Act: -0.1700
Data Index: 4345997 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.0821. Min Range: -10.0821
Max Act: 9.8946. Min Act: -0.1700
Data Index: 6881065 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.0821. Min Range: -10.0821
Max Act: 9.7696. Min Act: -0.1700
Data Index: 8280147 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.0821. Min Range: -10.0821
Max Act: 9.7696. Min Act: -0.1700
Data Index: 1844363 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.0821. Min Range: -10.0821
Max Act: 9.7071. Min Act: -0.1700
Data Index: 6905131 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.0821. Min Range: -10.0821
Max Act: 9.7071. Min Act: -0.1700
Data Index: 5570829 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.0821. Min Range: -10.0821
Max Act: 9.5821. Min Act: -0.1700
Data Index: 7569950 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.0821. Min Range: -10.0821
Max Act: 9.6446. Min Act: -0.1700
Data Index: 3257540 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.0821. Min Range: -10.0821
Max Act: 9.6446. Min Act: -0.1700
Data Index: 3904709 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.0821. Min Range: -10.0821
Max Act: 9.6446. Min Act: -0.1700
Data Index: 5988133 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.0821. Min Range: -10.0821
Max Act: 9.5821. Min Act: -0.1700
Data Index: 1111261 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.0821. Min Range: -10.0821
Max Act: 9.5821. Min Act: -0.1700
Data Index: 5000357 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.0821. Min Range: -10.0821
Max Act: 9.5821. Min Act: -0.1700
Data Index: 5430409 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.0821. Min Range: -10.0821
Max Act: 9.5821. Min Act: -0.1700
Data Index: 4769485 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.0821. Min Range: -10.0821
Max Act: 9.5821. Min Act: -0.1700
Data Index: 4191866 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.0821. Min Range: -10.0821
Max Act: 9.5821. Min Act: -0.1700
Data Index: 4350721 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.0821. Min Range: -10.0821
Max Act: 9.5821. Min Act: -0.1700
Data Index: 3691155 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #19