Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2091 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6582. Min Range: -8.6582
Max Act: 8.6582. Min Act: -0.1700
Data Index: 3280091 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6582. Min Range: -8.6582
Max Act: 8.4707. Min Act: -0.1700
Data Index: 4348537 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6582. Min Range: -8.6582
Max Act: 8.4707. Min Act: -0.1700
Data Index: 2878207 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6582. Min Range: -8.6582
Max Act: 8.4082. Min Act: -0.1700
Data Index: 2193282 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6582. Min Range: -8.6582
Max Act: 8.3457. Min Act: -0.1700
Data Index: 8255645 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6582. Min Range: -8.6582
Max Act: 8.2832. Min Act: -0.1700
Data Index: 37122 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6582. Min Range: -8.6582
Max Act: 8.2832. Min Act: -0.1700
Data Index: 739297 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6582. Min Range: -8.6582
Max Act: 8.2207. Min Act: -0.1700
Data Index: 2208320 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6582. Min Range: -8.6582
Max Act: 8.2207. Min Act: -0.1700
Data Index: 5792258 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6582. Min Range: -8.6582
Max Act: 8.1582. Min Act: -0.1700
Data Index: 7909506 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6582. Min Range: -8.6582
Max Act: 8.0332. Min Act: -0.1700
Data Index: 5472653 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6582. Min Range: -8.6582
Max Act: 8.0020. Min Act: -0.1700
Data Index: 5273138 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6582. Min Range: -8.6582
Max Act: 8.0020. Min Act: -0.1700
Data Index: 2973076 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6582. Min Range: -8.6582
Max Act: 7.9707. Min Act: -0.1700
Data Index: 3151030 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6582. Min Range: -8.6582
Max Act: 7.9082. Min Act: -0.1700
Data Index: 3820344 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6582. Min Range: -8.6582
Max Act: 7.8457. Min Act: -0.1700
Data Index: 5986140 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6582. Min Range: -8.6582
Max Act: 7.8770. Min Act: -0.1700
Data Index: 6154614 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6582. Min Range: -8.6582
Max Act: 7.8457. Min Act: -0.1700
Data Index: 7167934 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6582. Min Range: -8.6582
Max Act: 7.8145. Min Act: -0.1700
Data Index: 2851871 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6582. Min Range: -8.6582
Max Act: 7.8145. Min Act: -0.1700
Data Index: 3640370 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #19