Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3671 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.4642. Min Range: -10.4642
Max Act: 10.4642. Min Act: -0.1700
Data Index: 3692383 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.4642. Min Range: -10.4642
Max Act: 9.9017. Min Act: -0.1700
Data Index: 8483881 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.4642. Min Range: -10.4642
Max Act: 9.7767. Min Act: -0.1700
Data Index: 493428 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.4642. Min Range: -10.4642
Max Act: 9.4642. Min Act: -0.1700
Data Index: 5821615 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.4642. Min Range: -10.4642
Max Act: 9.4642. Min Act: -0.1700
Data Index: 5810500 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.4642. Min Range: -10.4642
Max Act: 9.4017. Min Act: -0.1700
Data Index: 7932652 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.4642. Min Range: -10.4642
Max Act: 9.3392. Min Act: -0.1700
Data Index: 8279293 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.4642. Min Range: -10.4642
Max Act: 9.2767. Min Act: -0.1700
Data Index: 4267799 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.4642. Min Range: -10.4642
Max Act: 9.2767. Min Act: -0.1700
Data Index: 603208 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.4642. Min Range: -10.4642
Max Act: 9.2767. Min Act: -0.1700
Data Index: 4016936 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.4642. Min Range: -10.4642
Max Act: 9.2142. Min Act: -0.1700
Data Index: 943643 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.4642. Min Range: -10.4642
Max Act: 9.2142. Min Act: -0.1700
Data Index: 4058055 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.4642. Min Range: -10.4642
Max Act: 9.2142. Min Act: -0.1700
Data Index: 7511382 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.4642. Min Range: -10.4642
Max Act: 9.1517. Min Act: -0.1700
Data Index: 5811539 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.4642. Min Range: -10.4642
Max Act: 9.1517. Min Act: -0.1700
Data Index: 3707040 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.4642. Min Range: -10.4642
Max Act: 9.1517. Min Act: -0.1700
Data Index: 8434606 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.4642. Min Range: -10.4642
Max Act: 9.1517. Min Act: -0.1700
Data Index: 831436 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.4642. Min Range: -10.4642
Max Act: 9.2142. Min Act: -0.1700
Data Index: 7398028 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.4642. Min Range: -10.4642
Max Act: 9.1517. Min Act: -0.1700
Data Index: 1638860 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.4642. Min Range: -10.4642
Max Act: 9.0892. Min Act: -0.1700
Data Index: 526546 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #19