Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 5118 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.3202. Min Range: -6.3202
Max Act: 6.3202. Min Act: -0.1700
Data Index: 7717762 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3202. Min Range: -6.3202
Max Act: 6.1952. Min Act: -0.1700
Data Index: 7283938 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3202. Min Range: -6.3202
Max Act: 6.1639. Min Act: -0.1700
Data Index: 2209364 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3202. Min Range: -6.3202
Max Act: 6.1327. Min Act: -0.1700
Data Index: 3978950 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3202. Min Range: -6.3202
Max Act: 6.0702. Min Act: -0.1700
Data Index: 5280094 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3202. Min Range: -6.3202
Max Act: 6.0389. Min Act: -0.1700
Data Index: 7251076 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3202. Min Range: -6.3202
Max Act: 6.0389. Min Act: -0.1700
Data Index: 2346215 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3202. Min Range: -6.3202
Max Act: 5.9764. Min Act: -0.1700
Data Index: 4611204 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3202. Min Range: -6.3202
Max Act: 6.0077. Min Act: -0.1700
Data Index: 1719828 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3202. Min Range: -6.3202
Max Act: 5.9452. Min Act: -0.1700
Data Index: 6844198 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3202. Min Range: -6.3202
Max Act: 5.9139. Min Act: -0.1700
Data Index: 4937170 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3202. Min Range: -6.3202
Max Act: 5.9452. Min Act: -0.1700
Data Index: 4070550 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3202. Min Range: -6.3202
Max Act: 5.8827. Min Act: -0.1700
Data Index: 1181795 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3202. Min Range: -6.3202
Max Act: 5.9452. Min Act: -0.1700
Data Index: 4810890 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3202. Min Range: -6.3202
Max Act: 5.8827. Min Act: -0.1700
Data Index: 5365961 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3202. Min Range: -6.3202
Max Act: 5.8827. Min Act: -0.1700
Data Index: 3974037 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3202. Min Range: -6.3202
Max Act: 5.8514. Min Act: -0.1700
Data Index: 5582982 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3202. Min Range: -6.3202
Max Act: 5.8514. Min Act: -0.1700
Data Index: 6373454 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3202. Min Range: -6.3202
Max Act: 5.8514. Min Act: -0.1700
Data Index: 599707 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3202. Min Range: -6.3202
Max Act: 5.8514. Min Act: -0.1700
Data Index: 2115229 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #19