Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5290 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9050. Min Range: -4.9050
Max Act: 4.9050. Min Act: -0.1700
Data Index: 4136565 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9050. Min Range: -4.9050
Max Act: 4.8425. Min Act: -0.1700
Data Index: 2161988 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9050. Min Range: -4.9050
Max Act: 4.8425. Min Act: -0.1700
Data Index: 1493002 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9050. Min Range: -4.9050
Max Act: 4.8425. Min Act: -0.1700
Data Index: 5185779 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9050. Min Range: -4.9050
Max Act: 4.8112. Min Act: -0.1700
Data Index: 646645 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9050. Min Range: -4.9050
Max Act: 4.7800. Min Act: -0.1700
Data Index: 170298 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9050. Min Range: -4.9050
Max Act: 4.7800. Min Act: -0.1700
Data Index: 6329255 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9050. Min Range: -4.9050
Max Act: 4.7487. Min Act: -0.1700
Data Index: 3091079 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9050. Min Range: -4.9050
Max Act: 4.7487. Min Act: -0.1700
Data Index: 3006110 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9050. Min Range: -4.9050
Max Act: 4.7175. Min Act: -0.1700
Data Index: 1228759 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9050. Min Range: -4.9050
Max Act: 4.6550. Min Act: -0.1700
Data Index: 5531550 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9050. Min Range: -4.9050
Max Act: 4.6862. Min Act: -0.1700
Data Index: 5369783 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9050. Min Range: -4.9050
Max Act: 4.6550. Min Act: -0.1700
Data Index: 6105084 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9050. Min Range: -4.9050
Max Act: 4.6550. Min Act: -0.1700
Data Index: 1774573 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9050. Min Range: -4.9050
Max Act: 4.6550. Min Act: -0.1700
Data Index: 4124623 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9050. Min Range: -4.9050
Max Act: 4.6550. Min Act: -0.1700
Data Index: 15637 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9050. Min Range: -4.9050
Max Act: 4.6550. Min Act: -0.1700
Data Index: 2161989 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9050. Min Range: -4.9050
Max Act: 4.6550. Min Act: -0.1700
Data Index: 1355222 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9050. Min Range: -4.9050
Max Act: 4.5925. Min Act: -0.1700
Data Index: 4791246 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9050. Min Range: -4.9050
Max Act: 4.6237. Min Act: -0.1700
Data Index: 3021848 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #19