Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2385 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.7474. Min Range: -5.7474
Max Act: 5.7474. Min Act: -0.1700
Data Index: 767897 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7474. Min Range: -5.7474
Max Act: 5.4661. Min Act: -0.1700
Data Index: 594283 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7474. Min Range: -5.7474
Max Act: 5.2161. Min Act: -0.1700
Data Index: 6893896 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7474. Min Range: -5.7474
Max Act: 5.1536. Min Act: -0.1700
Data Index: 1680277 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7474. Min Range: -5.7474
Max Act: 5.1849. Min Act: -0.1700
Data Index: 3328002 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7474. Min Range: -5.7474
Max Act: 5.0911. Min Act: -0.1700
Data Index: 4512787 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7474. Min Range: -5.7474
Max Act: 5.1224. Min Act: -0.1700
Data Index: 8227053 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7474. Min Range: -5.7474
Max Act: 5.0911. Min Act: -0.1700
Data Index: 6035681 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7474. Min Range: -5.7474
Max Act: 5.0911. Min Act: -0.1700
Data Index: 2412129 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7474. Min Range: -5.7474
Max Act: 5.0911. Min Act: -0.1700
Data Index: 4745147 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7474. Min Range: -5.7474
Max Act: 5.0286. Min Act: -0.1700
Data Index: 7181738 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7474. Min Range: -5.7474
Max Act: 5.0286. Min Act: -0.1700
Data Index: 2099374 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7474. Min Range: -5.7474
Max Act: 4.9974. Min Act: -0.1700
Data Index: 5662975 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7474. Min Range: -5.7474
Max Act: 5.0599. Min Act: -0.1700
Data Index: 7439205 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7474. Min Range: -5.7474
Max Act: 4.9974. Min Act: -0.1700
Data Index: 62051 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7474. Min Range: -5.7474
Max Act: 4.9661. Min Act: -0.1700
Data Index: 597855 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7474. Min Range: -5.7474
Max Act: 4.9661. Min Act: -0.1700
Data Index: 5933465 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7474. Min Range: -5.7474
Max Act: 4.9661. Min Act: -0.1700
Data Index: 2602891 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7474. Min Range: -5.7474
Max Act: 4.9974. Min Act: -0.1700
Data Index: 488554 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7474. Min Range: -5.7474
Max Act: 4.9661. Min Act: -0.1700
Data Index: 357072 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #19