Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6280 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2349. Min Range: -6.2349
Max Act: 6.2349. Min Act: -0.1700
Data Index: 4231486 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2349. Min Range: -6.2349
Max Act: 6.1099. Min Act: -0.1700
Data Index: 2296799 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2349. Min Range: -6.2349
Max Act: 6.0786. Min Act: -0.1700
Data Index: 1560307 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2349. Min Range: -6.2349
Max Act: 5.9849. Min Act: -0.1700
Data Index: 4435637 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2349. Min Range: -6.2349
Max Act: 5.9536. Min Act: -0.1700
Data Index: 3652926 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2349. Min Range: -6.2349
Max Act: 5.9224. Min Act: -0.1700
Data Index: 1989028 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2349. Min Range: -6.2349
Max Act: 5.9224. Min Act: -0.1700
Data Index: 7863213 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2349. Min Range: -6.2349
Max Act: 5.8911. Min Act: -0.1700
Data Index: 1305136 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2349. Min Range: -6.2349
Max Act: 5.8911. Min Act: -0.1700
Data Index: 7613565 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2349. Min Range: -6.2349
Max Act: 5.8599. Min Act: -0.1700
Data Index: 534878 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2349. Min Range: -6.2349
Max Act: 5.8599. Min Act: -0.1700
Data Index: 7943665 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2349. Min Range: -6.2349
Max Act: 5.8286. Min Act: -0.1700
Data Index: 5109215 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2349. Min Range: -6.2349
Max Act: 5.8286. Min Act: -0.1700
Data Index: 226434 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2349. Min Range: -6.2349
Max Act: 5.8286. Min Act: -0.1700
Data Index: 4315487 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2349. Min Range: -6.2349
Max Act: 5.8286. Min Act: -0.1700
Data Index: 8755265 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2349. Min Range: -6.2349
Max Act: 5.7661. Min Act: -0.1700
Data Index: 4539512 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2349. Min Range: -6.2349
Max Act: 5.7661. Min Act: -0.1700
Data Index: 3133397 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2349. Min Range: -6.2349
Max Act: 5.7661. Min Act: -0.1700
Data Index: 330399 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2349. Min Range: -6.2349
Max Act: 5.7661. Min Act: -0.1700
Data Index: 5697033 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2349. Min Range: -6.2349
Max Act: 5.7661. Min Act: -0.1700
Data Index: 7221494 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #19