Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2000 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.7613. Min Range: -9.7613
Max Act: 9.7613. Min Act: -0.1700
Data Index: 3020382 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.7613. Min Range: -9.7613
Max Act: 9.5738. Min Act: -0.1700
Data Index: 1229146 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.7613. Min Range: -9.7613
Max Act: 9.4488. Min Act: -0.1700
Data Index: 6646408 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.7613. Min Range: -9.7613
Max Act: 9.4488. Min Act: -0.1700
Data Index: 395981 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.7613. Min Range: -9.7613
Max Act: 9.5113. Min Act: -0.1700
Data Index: 898812 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.7613. Min Range: -9.7613
Max Act: 9.4488. Min Act: -0.1700
Data Index: 7395434 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.7613. Min Range: -9.7613
Max Act: 9.3863. Min Act: -0.1700
Data Index: 8319646 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.7613. Min Range: -9.7613
Max Act: 9.3238. Min Act: -0.1700
Data Index: 1119690 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.7613. Min Range: -9.7613
Max Act: 9.3238. Min Act: -0.1700
Data Index: 6404738 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.7613. Min Range: -9.7613
Max Act: 9.2613. Min Act: -0.1700
Data Index: 4726704 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.7613. Min Range: -9.7613
Max Act: 9.2613. Min Act: -0.1700
Data Index: 7428134 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.7613. Min Range: -9.7613
Max Act: 9.2613. Min Act: -0.1700
Data Index: 8603143 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.7613. Min Range: -9.7613
Max Act: 9.2613. Min Act: -0.1700
Data Index: 2246374 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.7613. Min Range: -9.7613
Max Act: 9.1988. Min Act: -0.1700
Data Index: 7331663 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.7613. Min Range: -9.7613
Max Act: 9.1363. Min Act: -0.1700
Data Index: 5218879 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.7613. Min Range: -9.7613
Max Act: 9.0738. Min Act: -0.1700
Data Index: 7687187 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.7613. Min Range: -9.7613
Max Act: 9.1363. Min Act: -0.1700
Data Index: 1354193 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.7613. Min Range: -9.7613
Max Act: 9.1363. Min Act: -0.1700
Data Index: 2247786 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.7613. Min Range: -9.7613
Max Act: 9.1988. Min Act: -0.1700
Data Index: 6223807 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.7613. Min Range: -9.7613
Max Act: 9.0738. Min Act: -0.1700
Data Index: 6319899 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #19