Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2721 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.7843. Min Range: -3.7843
Max Act: 3.7843. Min Act: -0.1700
Data Index: 3677172 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7843. Min Range: -3.7843
Max Act: 3.5653. Min Act: -0.1700
Data Index: 2791510 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7843. Min Range: -3.7843
Max Act: 3.4870. Min Act: -0.1700
Data Index: 8621063 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7843. Min Range: -3.7843
Max Act: 3.4557. Min Act: -0.1700
Data Index: 8300822 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7843. Min Range: -3.7843
Max Act: 3.4400. Min Act: -0.1700
Data Index: 1228415 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7843. Min Range: -3.7843
Max Act: 3.4243. Min Act: -0.1700
Data Index: 6930293 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7843. Min Range: -3.7843
Max Act: 3.4086. Min Act: -0.1700
Data Index: 4452118 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7843. Min Range: -3.7843
Max Act: 3.3930. Min Act: -0.1700
Data Index: 7521828 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7843. Min Range: -3.7843
Max Act: 3.3773. Min Act: -0.1700
Data Index: 227586 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7843. Min Range: -3.7843
Max Act: 3.3930. Min Act: -0.1700
Data Index: 2606206 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7843. Min Range: -3.7843
Max Act: 3.3459. Min Act: -0.1700
Data Index: 2136915 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7843. Min Range: -3.7843
Max Act: 3.3616. Min Act: -0.1700
Data Index: 2791502 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7843. Min Range: -3.7843
Max Act: 3.3773. Min Act: -0.1700
Data Index: 8384422 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7843. Min Range: -3.7843
Max Act: 3.3616. Min Act: -0.1700
Data Index: 1348548 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7843. Min Range: -3.7843
Max Act: 3.3616. Min Act: -0.1700
Data Index: 5405447 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7843. Min Range: -3.7843
Max Act: 3.3302. Min Act: -0.1700
Data Index: 6817094 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7843. Min Range: -3.7843
Max Act: 3.3459. Min Act: -0.1700
Data Index: 4849984 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7843. Min Range: -3.7843
Max Act: 3.3145. Min Act: -0.1700
Data Index: 1219851 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7843. Min Range: -3.7843
Max Act: 3.3302. Min Act: -0.1700
Data Index: 2056042 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7843. Min Range: -3.7843
Max Act: 3.3302. Min Act: -0.1700
Data Index: 7521829 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #19