Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2456 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.7368. Min Range: -5.7368
Max Act: 5.7368. Min Act: -0.1700
Data Index: 3714031 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7368. Min Range: -5.7368
Max Act: 5.6430. Min Act: -0.1700
Data Index: 5082235 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7368. Min Range: -5.7368
Max Act: 5.5805. Min Act: -0.1700
Data Index: 2285331 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7368. Min Range: -5.7368
Max Act: 5.4868. Min Act: -0.1700
Data Index: 8578296 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7368. Min Range: -5.7368
Max Act: 5.4243. Min Act: -0.1700
Data Index: 128056 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7368. Min Range: -5.7368
Max Act: 5.4243. Min Act: -0.1700
Data Index: 1664953 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7368. Min Range: -5.7368
Max Act: 5.4243. Min Act: -0.1700
Data Index: 914138 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7368. Min Range: -5.7368
Max Act: 5.4243. Min Act: -0.1700
Data Index: 1077014 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7368. Min Range: -5.7368
Max Act: 5.3305. Min Act: -0.1700
Data Index: 4191519 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7368. Min Range: -5.7368
Max Act: 5.3618. Min Act: -0.1700
Data Index: 5995125 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7368. Min Range: -5.7368
Max Act: 5.3618. Min Act: -0.1700
Data Index: 8578295 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7368. Min Range: -5.7368
Max Act: 5.3305. Min Act: -0.1700
Data Index: 6783280 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7368. Min Range: -5.7368
Max Act: 5.2993. Min Act: -0.1700
Data Index: 4312673 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7368. Min Range: -5.7368
Max Act: 5.2993. Min Act: -0.1700
Data Index: 2181173 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7368. Min Range: -5.7368
Max Act: 5.2993. Min Act: -0.1700
Data Index: 1139909 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7368. Min Range: -5.7368
Max Act: 5.2993. Min Act: -0.1700
Data Index: 1867621 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7368. Min Range: -5.7368
Max Act: 5.2993. Min Act: -0.1700
Data Index: 3422678 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7368. Min Range: -5.7368
Max Act: 5.2680. Min Act: -0.1700
Data Index: 4016332 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7368. Min Range: -5.7368
Max Act: 5.2680. Min Act: -0.1700
Data Index: 1109614 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7368. Min Range: -5.7368
Max Act: 5.2680. Min Act: -0.1700
Data Index: 1314982 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #19