Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1920 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.3273. Min Range: -4.3273
Max Act: 4.3273. Min Act: -0.1700
Data Index: 4482590 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3273. Min Range: -4.3273
Max Act: 4.3273. Min Act: -0.1700
Data Index: 7463843 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3273. Min Range: -4.3273
Max Act: 4.2648. Min Act: -0.1700
Data Index: 869332 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3273. Min Range: -4.3273
Max Act: 4.2336. Min Act: -0.1700
Data Index: 6163791 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3273. Min Range: -4.3273
Max Act: 4.2336. Min Act: -0.1700
Data Index: 1432719 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3273. Min Range: -4.3273
Max Act: 4.1710. Min Act: -0.1700
Data Index: 7482217 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3273. Min Range: -4.3273
Max Act: 4.2023. Min Act: -0.1700
Data Index: 2689247 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3273. Min Range: -4.3273
Max Act: 4.2023. Min Act: -0.1700
Data Index: 6465600 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3273. Min Range: -4.3273
Max Act: 4.1710. Min Act: -0.1700
Data Index: 445564 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3273. Min Range: -4.3273
Max Act: 4.1398. Min Act: -0.1700
Data Index: 2017558 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3273. Min Range: -4.3273
Max Act: 4.1398. Min Act: -0.1700
Data Index: 8748934 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3273. Min Range: -4.3273
Max Act: 4.1398. Min Act: -0.1700
Data Index: 6699907 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3273. Min Range: -4.3273
Max Act: 4.1398. Min Act: -0.1700
Data Index: 8031021 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3273. Min Range: -4.3273
Max Act: 4.1398. Min Act: -0.1700
Data Index: 2127197 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3273. Min Range: -4.3273
Max Act: 4.1398. Min Act: -0.1700
Data Index: 6163803 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3273. Min Range: -4.3273
Max Act: 4.1085. Min Act: -0.1700
Data Index: 6055562 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3273. Min Range: -4.3273
Max Act: 4.0773. Min Act: -0.1700
Data Index: 7144211 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3273. Min Range: -4.3273
Max Act: 4.0773. Min Act: -0.1700
Data Index: 438724 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3273. Min Range: -4.3273
Max Act: 4.0773. Min Act: -0.1700
Data Index: 4594866 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3273. Min Range: -4.3273
Max Act: 4.0773. Min Act: -0.1700
Data Index: 4012574 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #19