Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3299 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.8981. Min Range: -5.8981
Max Act: 5.8981. Min Act: -0.1700
Data Index: 2121461 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8981. Min Range: -5.8981
Max Act: 5.7731. Min Act: -0.1700
Data Index: 1054424 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8981. Min Range: -5.8981
Max Act: 5.6793. Min Act: -0.1700
Data Index: 3460095 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8981. Min Range: -5.8981
Max Act: 5.5543. Min Act: -0.1700
Data Index: 7065862 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8981. Min Range: -5.8981
Max Act: 5.5856. Min Act: -0.1700
Data Index: 2255997 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8981. Min Range: -5.8981
Max Act: 5.4918. Min Act: -0.1700
Data Index: 5484193 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8981. Min Range: -5.8981
Max Act: 5.4606. Min Act: -0.1700
Data Index: 6890563 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8981. Min Range: -5.8981
Max Act: 5.4293. Min Act: -0.1700
Data Index: 891460 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8981. Min Range: -5.8981
Max Act: 5.4918. Min Act: -0.1700
Data Index: 3991626 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8981. Min Range: -5.8981
Max Act: 5.3668. Min Act: -0.1700
Data Index: 153047 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8981. Min Range: -5.8981
Max Act: 5.3356. Min Act: -0.1700
Data Index: 3808771 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8981. Min Range: -5.8981
Max Act: 5.3356. Min Act: -0.1700
Data Index: 4135903 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8981. Min Range: -5.8981
Max Act: 5.3043. Min Act: -0.1700
Data Index: 5374371 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8981. Min Range: -5.8981
Max Act: 5.2731. Min Act: -0.1700
Data Index: 935065 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8981. Min Range: -5.8981
Max Act: 5.2731. Min Act: -0.1700
Data Index: 3992639 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8981. Min Range: -5.8981
Max Act: 5.2731. Min Act: -0.1700
Data Index: 5814577 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8981. Min Range: -5.8981
Max Act: 5.2731. Min Act: -0.1700
Data Index: 146125 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8981. Min Range: -5.8981
Max Act: 5.2418. Min Act: -0.1700
Data Index: 8732387 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8981. Min Range: -5.8981
Max Act: 5.2106. Min Act: -0.1700
Data Index: 8520994 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8981. Min Range: -5.8981
Max Act: 5.2106. Min Act: -0.1700
Data Index: 7843155 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #19