Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4074 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.5038. Min Range: -6.5038
Max Act: 6.5038. Min Act: -0.1700
Data Index: 8439011 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5038. Min Range: -6.5038
Max Act: 6.4100. Min Act: -0.1700
Data Index: 8385737 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5038. Min Range: -6.5038
Max Act: 6.3788. Min Act: -0.1700
Data Index: 7336240 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5038. Min Range: -6.5038
Max Act: 6.3788. Min Act: -0.1700
Data Index: 214294 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5038. Min Range: -6.5038
Max Act: 6.3475. Min Act: -0.1700
Data Index: 3887914 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5038. Min Range: -6.5038
Max Act: 6.3163. Min Act: -0.1700
Data Index: 8306216 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5038. Min Range: -6.5038
Max Act: 6.2538. Min Act: -0.1700
Data Index: 1518473 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5038. Min Range: -6.5038
Max Act: 6.2538. Min Act: -0.1700
Data Index: 4584600 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5038. Min Range: -6.5038
Max Act: 6.1913. Min Act: -0.1700
Data Index: 7004113 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5038. Min Range: -6.5038
Max Act: 6.1913. Min Act: -0.1700
Data Index: 6616704 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5038. Min Range: -6.5038
Max Act: 6.1288. Min Act: -0.1700
Data Index: 8206857 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5038. Min Range: -6.5038
Max Act: 6.1288. Min Act: -0.1700
Data Index: 4297161 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5038. Min Range: -6.5038
Max Act: 6.1288. Min Act: -0.1700
Data Index: 1189351 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5038. Min Range: -6.5038
Max Act: 6.1600. Min Act: -0.1700
Data Index: 7727116 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5038. Min Range: -6.5038
Max Act: 6.0975. Min Act: -0.1700
Data Index: 7757996 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5038. Min Range: -6.5038
Max Act: 6.1288. Min Act: -0.1700
Data Index: 4588921 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5038. Min Range: -6.5038
Max Act: 6.1288. Min Act: -0.1700
Data Index: 7418261 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5038. Min Range: -6.5038
Max Act: 6.1288. Min Act: -0.1700
Data Index: 6139573 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5038. Min Range: -6.5038
Max Act: 6.0975. Min Act: -0.1700
Data Index: 3010274 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5038. Min Range: -6.5038
Max Act: 6.0663. Min Act: -0.1700
Data Index: 1313548 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #19