Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 881 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.4365. Min Range: -8.4365
Max Act: 8.4365. Min Act: -0.1700
Data Index: 4536525 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4365. Min Range: -8.4365
Max Act: 8.3740. Min Act: -0.1700
Data Index: 2723588 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4365. Min Range: -8.4365
Max Act: 8.1240. Min Act: -0.1700
Data Index: 3774504 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4365. Min Range: -8.4365
Max Act: 8.0615. Min Act: -0.1700
Data Index: 393446 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4365. Min Range: -8.4365
Max Act: 8.0615. Min Act: -0.1700
Data Index: 7391839 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4365. Min Range: -8.4365
Max Act: 7.9990. Min Act: -0.1700
Data Index: 545647 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4365. Min Range: -8.4365
Max Act: 7.9678. Min Act: -0.1700
Data Index: 7017136 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4365. Min Range: -8.4365
Max Act: 7.8740. Min Act: -0.1700
Data Index: 3141962 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4365. Min Range: -8.4365
Max Act: 7.9053. Min Act: -0.1700
Data Index: 2096476 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4365. Min Range: -8.4365
Max Act: 7.8740. Min Act: -0.1700
Data Index: 1844966 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4365. Min Range: -8.4365
Max Act: 7.8428. Min Act: -0.1700
Data Index: 3169166 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4365. Min Range: -8.4365
Max Act: 7.8115. Min Act: -0.1700
Data Index: 4692279 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4365. Min Range: -8.4365
Max Act: 7.7490. Min Act: -0.1700
Data Index: 7836898 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4365. Min Range: -8.4365
Max Act: 7.7490. Min Act: -0.1700
Data Index: 5835977 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4365. Min Range: -8.4365
Max Act: 7.7178. Min Act: -0.1700
Data Index: 545643 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4365. Min Range: -8.4365
Max Act: 7.7178. Min Act: -0.1700
Data Index: 1264044 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4365. Min Range: -8.4365
Max Act: 7.6553. Min Act: -0.1700
Data Index: 8817440 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4365. Min Range: -8.4365
Max Act: 7.6553. Min Act: -0.1700
Data Index: 8389609 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4365. Min Range: -8.4365
Max Act: 7.5928. Min Act: -0.1700
Data Index: 1942571 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4365. Min Range: -8.4365
Max Act: 7.6865. Min Act: -0.1700
Data Index: 3817139 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #19