Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2234 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.6345. Min Range: -5.6345
Max Act: 5.6345. Min Act: -0.1700
Data Index: 1686013 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6345. Min Range: -5.6345
Max Act: 5.4783. Min Act: -0.1700
Data Index: 3616777 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6345. Min Range: -5.6345
Max Act: 5.4158. Min Act: -0.1700
Data Index: 2115378 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6345. Min Range: -5.6345
Max Act: 5.4158. Min Act: -0.1700
Data Index: 887835 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6345. Min Range: -5.6345
Max Act: 5.4158. Min Act: -0.1700
Data Index: 3540315 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6345. Min Range: -5.6345
Max Act: 5.3533. Min Act: -0.1700
Data Index: 6511956 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6345. Min Range: -5.6345
Max Act: 5.3533. Min Act: -0.1700
Data Index: 6507330 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6345. Min Range: -5.6345
Max Act: 5.2595. Min Act: -0.1700
Data Index: 6162732 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6345. Min Range: -5.6345
Max Act: 5.2283. Min Act: -0.1700
Data Index: 5940330 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6345. Min Range: -5.6345
Max Act: 5.1970. Min Act: -0.1700
Data Index: 3246514 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6345. Min Range: -5.6345
Max Act: 5.1658. Min Act: -0.1700
Data Index: 652722 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6345. Min Range: -5.6345
Max Act: 5.1658. Min Act: -0.1700
Data Index: 6752953 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6345. Min Range: -5.6345
Max Act: 5.1658. Min Act: -0.1700
Data Index: 6886541 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6345. Min Range: -5.6345
Max Act: 5.1345. Min Act: -0.1700
Data Index: 2718411 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6345. Min Range: -5.6345
Max Act: 5.1658. Min Act: -0.1700
Data Index: 7715211 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6345. Min Range: -5.6345
Max Act: 5.1658. Min Act: -0.1700
Data Index: 3217069 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6345. Min Range: -5.6345
Max Act: 5.1658. Min Act: -0.1700
Data Index: 8236289 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6345. Min Range: -5.6345
Max Act: 5.1345. Min Act: -0.1700
Data Index: 3738924 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6345. Min Range: -5.6345
Max Act: 5.1345. Min Act: -0.1700
Data Index: 4576319 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6345. Min Range: -5.6345
Max Act: 5.0408. Min Act: -0.1700
Data Index: 6854410 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #19