Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3440 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5174. Min Range: -6.5174
Max Act: 6.5174. Min Act: -0.1700
Data Index: 6515014 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5174. Min Range: -6.5174
Max Act: 6.4236. Min Act: -0.1700
Data Index: 3132275 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5174. Min Range: -6.5174
Max Act: 6.3611. Min Act: -0.1700
Data Index: 4355229 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5174. Min Range: -6.5174
Max Act: 6.3299. Min Act: -0.1700
Data Index: 4968565 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5174. Min Range: -6.5174
Max Act: 6.2986. Min Act: -0.1700
Data Index: 6257802 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5174. Min Range: -6.5174
Max Act: 6.2986. Min Act: -0.1699
Data Index: 6943430 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5174. Min Range: -6.5174
Max Act: 6.2986. Min Act: -0.1700
Data Index: 1342264 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5174. Min Range: -6.5174
Max Act: 6.2674. Min Act: -0.1700
Data Index: 737257 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5174. Min Range: -6.5174
Max Act: 6.2674. Min Act: -0.1700
Data Index: 4860123 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5174. Min Range: -6.5174
Max Act: 6.2361. Min Act: -0.1700
Data Index: 5768370 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5174. Min Range: -6.5174
Max Act: 6.2361. Min Act: -0.1700
Data Index: 936110 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5174. Min Range: -6.5174
Max Act: 6.2674. Min Act: -0.1700
Data Index: 2332854 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5174. Min Range: -6.5174
Max Act: 6.2674. Min Act: -0.1700
Data Index: 3397178 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5174. Min Range: -6.5174
Max Act: 6.2674. Min Act: -0.1700
Data Index: 6722323 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5174. Min Range: -6.5174
Max Act: 6.2361. Min Act: -0.1700
Data Index: 2336408 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5174. Min Range: -6.5174
Max Act: 6.2361. Min Act: -0.1700
Data Index: 4386461 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5174. Min Range: -6.5174
Max Act: 6.2674. Min Act: -0.1700
Data Index: 7641785 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5174. Min Range: -6.5174
Max Act: 6.1736. Min Act: -0.1700
Data Index: 231848 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5174. Min Range: -6.5174
Max Act: 6.2361. Min Act: -0.1700
Data Index: 2563650 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5174. Min Range: -6.5174
Max Act: 6.1736. Min Act: -0.1700
Data Index: 4520310 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #19