Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 306 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.3836. Min Range: -5.3836
Max Act: 5.3836. Min Act: -0.1700
Data Index: 982238 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3836. Min Range: -5.3836
Max Act: 5.3524. Min Act: -0.1700
Data Index: 8698459 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3836. Min Range: -5.3836
Max Act: 5.1024. Min Act: -0.1700
Data Index: 4438940 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3836. Min Range: -5.3836
Max Act: 5.0399. Min Act: -0.1700
Data Index: 2401296 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3836. Min Range: -5.3836
Max Act: 5.0711. Min Act: -0.1700
Data Index: 989266 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3836. Min Range: -5.3836
Max Act: 4.9774. Min Act: -0.1700
Data Index: 5850717 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3836. Min Range: -5.3836
Max Act: 4.9461. Min Act: -0.1700
Data Index: 5410647 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3836. Min Range: -5.3836
Max Act: 4.9149. Min Act: -0.1700
Data Index: 2528591 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3836. Min Range: -5.3836
Max Act: 4.9149. Min Act: -0.1700
Data Index: 852725 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3836. Min Range: -5.3836
Max Act: 4.9461. Min Act: -0.1700
Data Index: 3641293 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3836. Min Range: -5.3836
Max Act: 4.8836. Min Act: -0.1700
Data Index: 4237228 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3836. Min Range: -5.3836
Max Act: 4.9461. Min Act: -0.1700
Data Index: 2710471 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3836. Min Range: -5.3836
Max Act: 4.9149. Min Act: -0.1700
Data Index: 3303131 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3836. Min Range: -5.3836
Max Act: 4.9149. Min Act: -0.1700
Data Index: 7374630 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3836. Min Range: -5.3836
Max Act: 4.8836. Min Act: -0.1700
Data Index: 3715733 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3836. Min Range: -5.3836
Max Act: 4.8836. Min Act: -0.1700
Data Index: 3638365 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3836. Min Range: -5.3836
Max Act: 4.8524. Min Act: -0.1700
Data Index: 5655134 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3836. Min Range: -5.3836
Max Act: 4.8836. Min Act: -0.1700
Data Index: 523231 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3836. Min Range: -5.3836
Max Act: 4.8524. Min Act: -0.1700
Data Index: 5739569 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3836. Min Range: -5.3836
Max Act: 4.8524. Min Act: -0.1700
Data Index: 4826842 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #19