Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4068 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.3149. Min Range: -3.3149
Max Act: 3.3149. Min Act: -0.1700
Data Index: 2050751 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3149. Min Range: -3.3149
Max Act: 3.2678. Min Act: -0.1700
Data Index: 2050750 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3149. Min Range: -3.3149
Max Act: 3.2835. Min Act: -0.1700
Data Index: 1989196 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3149. Min Range: -3.3149
Max Act: 3.2049. Min Act: -0.1700
Data Index: 722473 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3149. Min Range: -3.3149
Max Act: 3.1892. Min Act: -0.1700
Data Index: 1282279 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3149. Min Range: -3.3149
Max Act: 3.1262. Min Act: -0.1700
Data Index: 4404893 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3149. Min Range: -3.3149
Max Act: 3.1420. Min Act: -0.1700
Data Index: 2329020 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3149. Min Range: -3.3149
Max Act: 3.1105. Min Act: -0.1700
Data Index: 4318549 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3149. Min Range: -3.3149
Max Act: 3.1105. Min Act: -0.1700
Data Index: 7347423 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3149. Min Range: -3.3149
Max Act: 3.1262. Min Act: -0.1700
Data Index: 1696984 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3149. Min Range: -3.3149
Max Act: 3.0947. Min Act: -0.1700
Data Index: 5178755 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3149. Min Range: -3.3149
Max Act: 3.1262. Min Act: -0.1700
Data Index: 6214912 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3149. Min Range: -3.3149
Max Act: 3.0947. Min Act: -0.1700
Data Index: 7254899 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3149. Min Range: -3.3149
Max Act: 3.0474. Min Act: -0.1700
Data Index: 6697287 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3149. Min Range: -3.3149
Max Act: 3.0474. Min Act: -0.1700
Data Index: 2356175 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3149. Min Range: -3.3149
Max Act: 3.0789. Min Act: -0.1700
Data Index: 4645302 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3149. Min Range: -3.3149
Max Act: 3.0474. Min Act: -0.1700
Data Index: 2840762 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3149. Min Range: -3.3149
Max Act: 3.0316. Min Act: -0.1700
Data Index: 107400 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3149. Min Range: -3.3149
Max Act: 3.0474. Min Act: -0.1700
Data Index: 7030893 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3149. Min Range: -3.3149
Max Act: 3.0316. Min Act: -0.1700
Data Index: 6163423 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #19