Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3734 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2887. Min Range: -6.2887
Max Act: 6.2887. Min Act: -0.1700
Data Index: 1036457 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2887. Min Range: -6.2887
Max Act: 6.2262. Min Act: -0.1700
Data Index: 3303593 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2887. Min Range: -6.2887
Max Act: 6.2262. Min Act: -0.1700
Data Index: 5954671 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2887. Min Range: -6.2887
Max Act: 6.2262. Min Act: -0.1700
Data Index: 6415309 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2887. Min Range: -6.2887
Max Act: 6.1950. Min Act: -0.1700
Data Index: 4998155 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2887. Min Range: -6.2887
Max Act: 6.1637. Min Act: -0.1700
Data Index: 8241904 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2887. Min Range: -6.2887
Max Act: 6.1637. Min Act: -0.1700
Data Index: 4757791 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2887. Min Range: -6.2887
Max Act: 6.1325. Min Act: -0.1700
Data Index: 5165549 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2887. Min Range: -6.2887
Max Act: 6.1325. Min Act: -0.1700
Data Index: 1090010 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2887. Min Range: -6.2887
Max Act: 6.1325. Min Act: -0.1700
Data Index: 8153060 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2887. Min Range: -6.2887
Max Act: 6.1325. Min Act: -0.1700
Data Index: 6816958 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2887. Min Range: -6.2887
Max Act: 6.1325. Min Act: -0.1700
Data Index: 6985916 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2887. Min Range: -6.2887
Max Act: 6.1012. Min Act: -0.1700
Data Index: 6041020 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2887. Min Range: -6.2887
Max Act: 6.1012. Min Act: -0.1700
Data Index: 5536973 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2887. Min Range: -6.2887
Max Act: 6.1012. Min Act: -0.1700
Data Index: 8462692 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2887. Min Range: -6.2887
Max Act: 6.1012. Min Act: -0.1700
Data Index: 8370130 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2887. Min Range: -6.2887
Max Act: 6.0700. Min Act: -0.1700
Data Index: 6895435 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2887. Min Range: -6.2887
Max Act: 6.0700. Min Act: -0.1700
Data Index: 3600333 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2887. Min Range: -6.2887
Max Act: 6.0700. Min Act: -0.1700
Data Index: 3961925 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2887. Min Range: -6.2887
Max Act: 6.0700. Min Act: -0.1700
Data Index: 8220908 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #19