Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3926 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.7900. Min Range: -4.7900
Max Act: 4.7900. Min Act: -0.1700
Data Index: 764020 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7900. Min Range: -4.7900
Max Act: 4.7900. Min Act: -0.1700
Data Index: 7243637 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7900. Min Range: -4.7900
Max Act: 4.7275. Min Act: -0.1700
Data Index: 3303396 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7900. Min Range: -4.7900
Max Act: 4.6338. Min Act: -0.1700
Data Index: 5875686 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7900. Min Range: -4.7900
Max Act: 4.6338. Min Act: -0.1700
Data Index: 4491094 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7900. Min Range: -4.7900
Max Act: 4.6338. Min Act: -0.1700
Data Index: 8173021 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7900. Min Range: -4.7900
Max Act: 4.6025. Min Act: -0.1700
Data Index: 3936618 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7900. Min Range: -4.7900
Max Act: 4.6338. Min Act: -0.1700
Data Index: 3569325 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7900. Min Range: -4.7900
Max Act: 4.5400. Min Act: -0.1700
Data Index: 8639157 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7900. Min Range: -4.7900
Max Act: 4.5400. Min Act: -0.1700
Data Index: 8075039 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7900. Min Range: -4.7900
Max Act: 4.5088. Min Act: -0.1700
Data Index: 4896823 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7900. Min Range: -4.7900
Max Act: 4.5088. Min Act: -0.1700
Data Index: 3135147 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7900. Min Range: -4.7900
Max Act: 4.4775. Min Act: -0.1700
Data Index: 7819651 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7900. Min Range: -4.7900
Max Act: 4.4775. Min Act: -0.1700
Data Index: 7641734 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7900. Min Range: -4.7900
Max Act: 4.4775. Min Act: -0.1700
Data Index: 6382847 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7900. Min Range: -4.7900
Max Act: 4.4775. Min Act: -0.1700
Data Index: 1559832 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7900. Min Range: -4.7900
Max Act: 4.4463. Min Act: -0.1700
Data Index: 7654793 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7900. Min Range: -4.7900
Max Act: 4.4775. Min Act: -0.1700
Data Index: 2692304 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7900. Min Range: -4.7900
Max Act: 4.4150. Min Act: -0.1700
Data Index: 4963293 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7900. Min Range: -4.7900
Max Act: 4.4150. Min Act: -0.1700
Data Index: 1760759 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #19