Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 396 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.4298. Min Range: -3.4298
Max Act: 3.4298. Min Act: -0.1700
Data Index: 4972990 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4298. Min Range: -3.4298
Max Act: 3.3985. Min Act: -0.1700
Data Index: 7710147 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4298. Min Range: -3.4298
Max Act: 3.3985. Min Act: -0.1700
Data Index: 733619 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4298. Min Range: -3.4298
Max Act: 3.3671. Min Act: -0.1700
Data Index: 2236341 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4298. Min Range: -3.4298
Max Act: 3.3201. Min Act: -0.1700
Data Index: 1865025 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4298. Min Range: -3.4298
Max Act: 3.3201. Min Act: -0.1700
Data Index: 3158264 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4298. Min Range: -3.4298
Max Act: 3.3044. Min Act: -0.1700
Data Index: 59814 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4298. Min Range: -3.4298
Max Act: 3.3358. Min Act: -0.1700
Data Index: 5420150 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4298. Min Range: -3.4298
Max Act: 3.3044. Min Act: -0.1700
Data Index: 3663134 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4298. Min Range: -3.4298
Max Act: 3.3044. Min Act: -0.1700
Data Index: 591202 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4298. Min Range: -3.4298
Max Act: 3.2887. Min Act: -0.1700
Data Index: 19672 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4298. Min Range: -3.4298
Max Act: 3.2887. Min Act: -0.1700
Data Index: 4672203 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4298. Min Range: -3.4298
Max Act: 3.2887. Min Act: -0.1700
Data Index: 6539275 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4298. Min Range: -3.4298
Max Act: 3.3044. Min Act: -0.1700
Data Index: 3754042 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4298. Min Range: -3.4298
Max Act: 3.2730. Min Act: -0.1700
Data Index: 7293361 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4298. Min Range: -3.4298
Max Act: 3.2730. Min Act: -0.1700
Data Index: 7687070 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4298. Min Range: -3.4298
Max Act: 3.2415. Min Act: -0.1700
Data Index: 2163628 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4298. Min Range: -3.4298
Max Act: 3.2730. Min Act: -0.1700
Data Index: 1912844 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4298. Min Range: -3.4298
Max Act: 3.2730. Min Act: -0.1700
Data Index: 6680617 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4298. Min Range: -3.4298
Max Act: 3.2887. Min Act: -0.1700
Data Index: 72517 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #19