Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1794 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.6293. Min Range: -5.6293
Max Act: 5.6293. Min Act: -0.1700
Data Index: 7904633 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6293. Min Range: -5.6293
Max Act: 5.5981. Min Act: -0.1700
Data Index: 1486991 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6293. Min Range: -5.6293
Max Act: 5.5668. Min Act: -0.1700
Data Index: 6856516 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6293. Min Range: -5.6293
Max Act: 5.5043. Min Act: -0.1700
Data Index: 6407276 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6293. Min Range: -5.6293
Max Act: 5.5356. Min Act: -0.1700
Data Index: 7439770 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6293. Min Range: -5.6293
Max Act: 5.5043. Min Act: -0.1700
Data Index: 5150723 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6293. Min Range: -5.6293
Max Act: 5.4731. Min Act: -0.1700
Data Index: 233992 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6293. Min Range: -5.6293
Max Act: 5.4106. Min Act: -0.1700
Data Index: 5351569 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6293. Min Range: -5.6293
Max Act: 5.3481. Min Act: -0.1700
Data Index: 2625872 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6293. Min Range: -5.6293
Max Act: 5.3793. Min Act: -0.1700
Data Index: 7433876 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6293. Min Range: -5.6293
Max Act: 5.3481. Min Act: -0.1700
Data Index: 6901222 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6293. Min Range: -5.6293
Max Act: 5.3793. Min Act: -0.1700
Data Index: 3811605 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6293. Min Range: -5.6293
Max Act: 5.3481. Min Act: -0.1700
Data Index: 6719750 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6293. Min Range: -5.6293
Max Act: 5.3481. Min Act: -0.1700
Data Index: 4666158 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6293. Min Range: -5.6293
Max Act: 5.3481. Min Act: -0.1700
Data Index: 2957815 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6293. Min Range: -5.6293
Max Act: 5.3481. Min Act: -0.1700
Data Index: 8220068 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6293. Min Range: -5.6293
Max Act: 5.3168. Min Act: -0.1700
Data Index: 3735684 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6293. Min Range: -5.6293
Max Act: 5.3168. Min Act: -0.1700
Data Index: 2346349 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6293. Min Range: -5.6293
Max Act: 5.3481. Min Act: -0.1700
Data Index: 3691556 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6293. Min Range: -5.6293
Max Act: 5.2856. Min Act: -0.1700
Data Index: 6455946 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #19