Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4273 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0383. Min Range: -6.0383
Max Act: 6.0383. Min Act: -0.1700
Data Index: 6191149 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0383. Min Range: -6.0383
Max Act: 6.0071. Min Act: -0.1700
Data Index: 7698705 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0383. Min Range: -6.0383
Max Act: 5.9758. Min Act: -0.1700
Data Index: 3777844 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0383. Min Range: -6.0383
Max Act: 5.9133. Min Act: -0.1700
Data Index: 699693 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0383. Min Range: -6.0383
Max Act: 5.8821. Min Act: -0.1700
Data Index: 7698706 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0383. Min Range: -6.0383
Max Act: 5.8196. Min Act: -0.1700
Data Index: 5877140 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0383. Min Range: -6.0383
Max Act: 5.7883. Min Act: -0.1700
Data Index: 7339442 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0383. Min Range: -6.0383
Max Act: 5.7883. Min Act: -0.1700
Data Index: 6444352 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0383. Min Range: -6.0383
Max Act: 5.7571. Min Act: -0.1700
Data Index: 760692 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0383. Min Range: -6.0383
Max Act: 5.7571. Min Act: -0.1700
Data Index: 6653253 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0383. Min Range: -6.0383
Max Act: 5.7571. Min Act: -0.1700
Data Index: 2097898 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0383. Min Range: -6.0383
Max Act: 5.6946. Min Act: -0.1700
Data Index: 7782080 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0383. Min Range: -6.0383
Max Act: 5.6633. Min Act: -0.1700
Data Index: 2885183 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0383. Min Range: -6.0383
Max Act: 5.6008. Min Act: -0.1700
Data Index: 446114 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0383. Min Range: -6.0383
Max Act: 5.6321. Min Act: -0.1700
Data Index: 1020190 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0383. Min Range: -6.0383
Max Act: 5.6321. Min Act: -0.1700
Data Index: 4609919 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0383. Min Range: -6.0383
Max Act: 5.6321. Min Act: -0.1700
Data Index: 1000351 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0383. Min Range: -6.0383
Max Act: 5.6321. Min Act: -0.1700
Data Index: 6818454 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0383. Min Range: -6.0383
Max Act: 5.6321. Min Act: -0.1700
Data Index: 5322310 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0383. Min Range: -6.0383
Max Act: 5.6321. Min Act: -0.1700
Data Index: 7334660 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #19