Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 447 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.3347. Min Range: -7.3347
Max Act: 7.3347. Min Act: -0.1700
Data Index: 215882 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3347. Min Range: -7.3347
Max Act: 7.3035. Min Act: -0.1700
Data Index: 5230550 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3347. Min Range: -7.3347
Max Act: 7.3347. Min Act: -0.1700
Data Index: 5903405 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3347. Min Range: -7.3347
Max Act: 7.2722. Min Act: -0.1700
Data Index: 4259906 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3347. Min Range: -7.3347
Max Act: 7.2722. Min Act: -0.1700
Data Index: 8821297 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3347. Min Range: -7.3347
Max Act: 7.1785. Min Act: -0.1700
Data Index: 2669142 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3347. Min Range: -7.3347
Max Act: 7.2097. Min Act: -0.1700
Data Index: 5352077 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3347. Min Range: -7.3347
Max Act: 7.1785. Min Act: -0.1700
Data Index: 4581215 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3347. Min Range: -7.3347
Max Act: 7.1472. Min Act: -0.1700
Data Index: 8693330 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3347. Min Range: -7.3347
Max Act: 7.1785. Min Act: -0.1700
Data Index: 67035 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3347. Min Range: -7.3347
Max Act: 7.1160. Min Act: -0.1700
Data Index: 184459 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3347. Min Range: -7.3347
Max Act: 7.0847. Min Act: -0.1700
Data Index: 5870490 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3347. Min Range: -7.3347
Max Act: 7.0847. Min Act: -0.1700
Data Index: 3713289 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3347. Min Range: -7.3347
Max Act: 7.0535. Min Act: -0.1700
Data Index: 6117497 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3347. Min Range: -7.3347
Max Act: 7.0535. Min Act: -0.1700
Data Index: 2417770 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3347. Min Range: -7.3347
Max Act: 7.0535. Min Act: -0.1700
Data Index: 2529603 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3347. Min Range: -7.3347
Max Act: 7.0535. Min Act: -0.1700
Data Index: 1219550 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3347. Min Range: -7.3347
Max Act: 7.0222. Min Act: -0.1700
Data Index: 102320 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3347. Min Range: -7.3347
Max Act: 7.0222. Min Act: -0.1700
Data Index: 1292571 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3347. Min Range: -7.3347
Max Act: 6.9910. Min Act: -0.1700
Data Index: 3733499 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #19