Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1578 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.2137. Min Range: -5.2137
Max Act: 5.2137. Min Act: -0.1700
Data Index: 726996 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2137. Min Range: -5.2137
Max Act: 5.0575. Min Act: -0.1700
Data Index: 3360228 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2137. Min Range: -5.2137
Max Act: 5.0262. Min Act: -0.1700
Data Index: 1162794 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2137. Min Range: -5.2137
Max Act: 5.0262. Min Act: -0.1700
Data Index: 5569832 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2137. Min Range: -5.2137
Max Act: 4.9637. Min Act: -0.1700
Data Index: 6018818 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2137. Min Range: -5.2137
Max Act: 4.9950. Min Act: -0.1700
Data Index: 2786719 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2137. Min Range: -5.2137
Max Act: 4.9637. Min Act: -0.1700
Data Index: 1028264 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2137. Min Range: -5.2137
Max Act: 4.9637. Min Act: -0.1700
Data Index: 7653586 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2137. Min Range: -5.2137
Max Act: 4.9325. Min Act: -0.1700
Data Index: 4434224 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2137. Min Range: -5.2137
Max Act: 4.9325. Min Act: -0.1700
Data Index: 594982 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2137. Min Range: -5.2137
Max Act: 4.9325. Min Act: -0.1700
Data Index: 6422126 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2137. Min Range: -5.2137
Max Act: 4.8700. Min Act: -0.1700
Data Index: 2768775 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2137. Min Range: -5.2137
Max Act: 4.9012. Min Act: -0.1700
Data Index: 5399368 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2137. Min Range: -5.2137
Max Act: 4.9012. Min Act: -0.1700
Data Index: 214056 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2137. Min Range: -5.2137
Max Act: 4.9012. Min Act: -0.1700
Data Index: 959838 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2137. Min Range: -5.2137
Max Act: 4.9012. Min Act: -0.1700
Data Index: 2414992 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2137. Min Range: -5.2137
Max Act: 4.9012. Min Act: -0.1700
Data Index: 7930055 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2137. Min Range: -5.2137
Max Act: 4.8700. Min Act: -0.1700
Data Index: 4023884 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2137. Min Range: -5.2137
Max Act: 4.8387. Min Act: -0.1700
Data Index: 572629 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2137. Min Range: -5.2137
Max Act: 4.8700. Min Act: -0.1700
Data Index: 80116 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #19