Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4959 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.1078. Min Range: -4.1078
Max Act: 4.1078. Min Act: -0.1700
Data Index: 7105061 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1078. Min Range: -4.1078
Max Act: 4.0766. Min Act: -0.1700
Data Index: 5769690 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1078. Min Range: -4.1078
Max Act: 4.0453. Min Act: -0.1700
Data Index: 6241165 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1078. Min Range: -4.1078
Max Act: 3.9828. Min Act: -0.1700
Data Index: 926281 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1078. Min Range: -4.1078
Max Act: 3.9515. Min Act: -0.1700
Data Index: 1486321 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1078. Min Range: -4.1078
Max Act: 3.9515. Min Act: -0.1700
Data Index: 967151 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1078. Min Range: -4.1078
Max Act: 3.9203. Min Act: -0.1700
Data Index: 4640103 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1078. Min Range: -4.1078
Max Act: 3.8890. Min Act: -0.1700
Data Index: 7782983 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1078. Min Range: -4.1078
Max Act: 3.8890. Min Act: -0.1700
Data Index: 214616 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1078. Min Range: -4.1078
Max Act: 3.8577. Min Act: -0.1700
Data Index: 4178490 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1078. Min Range: -4.1078
Max Act: 3.8577. Min Act: -0.1700
Data Index: 2267492 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1078. Min Range: -4.1078
Max Act: 3.8577. Min Act: -0.1700
Data Index: 7276344 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1078. Min Range: -4.1078
Max Act: 3.8577. Min Act: -0.1700
Data Index: 8071368 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1078. Min Range: -4.1078
Max Act: 3.8577. Min Act: -0.1700
Data Index: 66295 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1078. Min Range: -4.1078
Max Act: 3.8421. Min Act: -0.1700
Data Index: 1081493 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1078. Min Range: -4.1078
Max Act: 3.8577. Min Act: -0.1700
Data Index: 6758164 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1078. Min Range: -4.1078
Max Act: 3.8108. Min Act: -0.1700
Data Index: 4565974 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1078. Min Range: -4.1078
Max Act: 3.8108. Min Act: -0.1700
Data Index: 5906878 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1078. Min Range: -4.1078
Max Act: 3.8265. Min Act: -0.1700
Data Index: 3071651 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1078. Min Range: -4.1078
Max Act: 3.8265. Min Act: -0.1700
Data Index: 3208432 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #19