Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2575 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4209. Min Range: -7.4209
Max Act: 7.4209. Min Act: -0.1700
Data Index: 4615108 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4209. Min Range: -7.4209
Max Act: 7.3272. Min Act: -0.1700
Data Index: 8753871 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4209. Min Range: -7.4209
Max Act: 7.2959. Min Act: -0.1700
Data Index: 6864007 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4209. Min Range: -7.4209
Max Act: 7.2022. Min Act: -0.1700
Data Index: 4529946 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4209. Min Range: -7.4209
Max Act: 7.2022. Min Act: -0.1700
Data Index: 4799561 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4209. Min Range: -7.4209
Max Act: 7.1084. Min Act: -0.1700
Data Index: 5953196 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4209. Min Range: -7.4209
Max Act: 7.0772. Min Act: -0.1700
Data Index: 6886585 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4209. Min Range: -7.4209
Max Act: 7.0772. Min Act: -0.1700
Data Index: 8001218 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4209. Min Range: -7.4209
Max Act: 7.0459. Min Act: -0.1700
Data Index: 5083892 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4209. Min Range: -7.4209
Max Act: 7.0459. Min Act: -0.1700
Data Index: 3672210 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4209. Min Range: -7.4209
Max Act: 7.0147. Min Act: -0.1700
Data Index: 6023726 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4209. Min Range: -7.4209
Max Act: 6.9522. Min Act: -0.1700
Data Index: 216020 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4209. Min Range: -7.4209
Max Act: 6.8897. Min Act: -0.1700
Data Index: 250651 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4209. Min Range: -7.4209
Max Act: 6.9209. Min Act: -0.1700
Data Index: 400178 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4209. Min Range: -7.4209
Max Act: 6.8897. Min Act: -0.1700
Data Index: 914049 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4209. Min Range: -7.4209
Max Act: 6.8272. Min Act: -0.1700
Data Index: 7925144 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4209. Min Range: -7.4209
Max Act: 6.7959. Min Act: -0.1700
Data Index: 1324546 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4209. Min Range: -7.4209
Max Act: 6.7959. Min Act: -0.1700
Data Index: 3506652 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4209. Min Range: -7.4209
Max Act: 6.7647. Min Act: -0.1700
Data Index: 2387951 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4209. Min Range: -7.4209
Max Act: 6.7959. Min Act: -0.1700
Data Index: 7428727 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #19