Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3581 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0749. Min Range: -6.0749
Max Act: 6.0749. Min Act: -0.1700
Data Index: 1872942 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0749. Min Range: -6.0749
Max Act: 5.9499. Min Act: -0.1700
Data Index: 1850074 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0749. Min Range: -6.0749
Max Act: 5.9499. Min Act: -0.1700
Data Index: 5324213 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0749. Min Range: -6.0749
Max Act: 5.9186. Min Act: -0.1700
Data Index: 8625821 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0749. Min Range: -6.0749
Max Act: 5.9186. Min Act: -0.1700
Data Index: 8428565 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0749. Min Range: -6.0749
Max Act: 5.9186. Min Act: -0.1700
Data Index: 5579105 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0749. Min Range: -6.0749
Max Act: 5.9186. Min Act: -0.1700
Data Index: 982054 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0749. Min Range: -6.0749
Max Act: 5.9499. Min Act: -0.1700
Data Index: 103463 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0749. Min Range: -6.0749
Max Act: 5.9186. Min Act: -0.1700
Data Index: 6196138 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0749. Min Range: -6.0749
Max Act: 5.8561. Min Act: -0.1700
Data Index: 5333010 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0749. Min Range: -6.0749
Max Act: 5.8561. Min Act: -0.1700
Data Index: 7925294 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0749. Min Range: -6.0749
Max Act: 5.8561. Min Act: -0.1700
Data Index: 7845098 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0749. Min Range: -6.0749
Max Act: 5.8561. Min Act: -0.1700
Data Index: 7739840 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0749. Min Range: -6.0749
Max Act: 5.7936. Min Act: -0.1700
Data Index: 3174701 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0749. Min Range: -6.0749
Max Act: 5.8249. Min Act: -0.1700
Data Index: 8309758 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0749. Min Range: -6.0749
Max Act: 5.8249. Min Act: -0.1700
Data Index: 3228199 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0749. Min Range: -6.0749
Max Act: 5.8249. Min Act: -0.1700
Data Index: 1085274 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0749. Min Range: -6.0749
Max Act: 5.8249. Min Act: -0.1700
Data Index: 470655 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0749. Min Range: -6.0749
Max Act: 5.8249. Min Act: -0.1700
Data Index: 3238883 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0749. Min Range: -6.0749
Max Act: 5.8249. Min Act: -0.1700
Data Index: 7084836 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #19