Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4580 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3662. Min Range: -7.3662
Max Act: 7.3662. Min Act: -0.1700
Data Index: 8624380 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3662. Min Range: -7.3662
Max Act: 7.2724. Min Act: -0.1700
Data Index: 8476344 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3662. Min Range: -7.3662
Max Act: 7.2412. Min Act: -0.1700
Data Index: 2102398 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3662. Min Range: -7.3662
Max Act: 7.1787. Min Act: -0.1700
Data Index: 1655528 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3662. Min Range: -7.3662
Max Act: 7.1787. Min Act: -0.1700
Data Index: 3492358 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3662. Min Range: -7.3662
Max Act: 7.1474. Min Act: -0.1700
Data Index: 842488 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3662. Min Range: -7.3662
Max Act: 7.0537. Min Act: -0.1700
Data Index: 2391669 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3662. Min Range: -7.3662
Max Act: 7.0224. Min Act: -0.1700
Data Index: 5557683 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3662. Min Range: -7.3662
Max Act: 6.9912. Min Act: -0.1700
Data Index: 6946054 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3662. Min Range: -7.3662
Max Act: 6.9912. Min Act: -0.1700
Data Index: 4645425 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3662. Min Range: -7.3662
Max Act: 6.8662. Min Act: -0.1700
Data Index: 1527750 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3662. Min Range: -7.3662
Max Act: 6.8662. Min Act: -0.1700
Data Index: 1372590 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3662. Min Range: -7.3662
Max Act: 6.8349. Min Act: -0.1700
Data Index: 2590630 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3662. Min Range: -7.3662
Max Act: 6.8037. Min Act: -0.1700
Data Index: 3196928 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3662. Min Range: -7.3662
Max Act: 6.7724. Min Act: -0.1700
Data Index: 3235715 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3662. Min Range: -7.3662
Max Act: 6.7724. Min Act: -0.1700
Data Index: 5634522 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3662. Min Range: -7.3662
Max Act: 6.7724. Min Act: -0.1700
Data Index: 2119076 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3662. Min Range: -7.3662
Max Act: 6.7724. Min Act: -0.1700
Data Index: 2956429 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3662. Min Range: -7.3662
Max Act: 6.7724. Min Act: -0.1700
Data Index: 6572833 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3662. Min Range: -7.3662
Max Act: 6.8037. Min Act: -0.1700
Data Index: 3357521 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #19