Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2092 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1362. Min Range: -7.1362
Max Act: 7.1362. Min Act: -0.1700
Data Index: 5270101 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1362. Min Range: -7.1362
Max Act: 6.9175. Min Act: -0.1700
Data Index: 8227445 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1362. Min Range: -7.1362
Max Act: 6.7925. Min Act: -0.1700
Data Index: 1091021 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1362. Min Range: -7.1362
Max Act: 6.7612. Min Act: -0.1700
Data Index: 4289691 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1362. Min Range: -7.1362
Max Act: 6.7612. Min Act: -0.1700
Data Index: 1963475 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1362. Min Range: -7.1362
Max Act: 6.7300. Min Act: -0.1700
Data Index: 8519194 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1362. Min Range: -7.1362
Max Act: 6.6050. Min Act: -0.1700
Data Index: 307213 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1362. Min Range: -7.1362
Max Act: 6.6050. Min Act: -0.1700
Data Index: 2354147 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1362. Min Range: -7.1362
Max Act: 6.5737. Min Act: -0.1700
Data Index: 7559970 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1362. Min Range: -7.1362
Max Act: 6.5425. Min Act: -0.1700
Data Index: 3973747 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1362. Min Range: -7.1362
Max Act: 6.5425. Min Act: -0.1700
Data Index: 1520929 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1362. Min Range: -7.1362
Max Act: 6.5112. Min Act: -0.1700
Data Index: 6299423 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1362. Min Range: -7.1362
Max Act: 6.5112. Min Act: -0.1700
Data Index: 4105571 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1362. Min Range: -7.1362
Max Act: 6.4800. Min Act: -0.1700
Data Index: 844943 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1362. Min Range: -7.1362
Max Act: 6.4487. Min Act: -0.1700
Data Index: 6623473 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1362. Min Range: -7.1362
Max Act: 6.4175. Min Act: -0.1700
Data Index: 2950055 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1362. Min Range: -7.1362
Max Act: 6.3862. Min Act: -0.1700
Data Index: 551027 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1362. Min Range: -7.1362
Max Act: 6.3550. Min Act: -0.1700
Data Index: 8579180 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1362. Min Range: -7.1362
Max Act: 6.3550. Min Act: -0.1700
Data Index: 6417273 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1362. Min Range: -7.1362
Max Act: 6.3550. Min Act: -0.1700
Data Index: 7621322 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #19