Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3515 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0928. Min Range: -5.0928
Max Act: 5.0928. Min Act: -0.1700
Data Index: 2016941 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0928. Min Range: -5.0928
Max Act: 4.9678. Min Act: -0.1700
Data Index: 1336308 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0928. Min Range: -5.0928
Max Act: 4.9991. Min Act: -0.1700
Data Index: 8395421 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0928. Min Range: -5.0928
Max Act: 4.9991. Min Act: -0.1700
Data Index: 7965484 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0928. Min Range: -5.0928
Max Act: 4.9991. Min Act: -0.1700
Data Index: 4334291 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0928. Min Range: -5.0928
Max Act: 4.9366. Min Act: -0.1700
Data Index: 154595 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0928. Min Range: -5.0928
Max Act: 4.9366. Min Act: -0.1700
Data Index: 8224701 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0928. Min Range: -5.0928
Max Act: 4.9053. Min Act: -0.1700
Data Index: 3266699 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0928. Min Range: -5.0928
Max Act: 4.9053. Min Act: -0.1700
Data Index: 3497721 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0928. Min Range: -5.0928
Max Act: 4.8741. Min Act: -0.1700
Data Index: 2429857 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0928. Min Range: -5.0928
Max Act: 4.8428. Min Act: -0.1700
Data Index: 8217555 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0928. Min Range: -5.0928
Max Act: 4.8428. Min Act: -0.1700
Data Index: 7183730 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0928. Min Range: -5.0928
Max Act: 4.8116. Min Act: -0.1700
Data Index: 5895241 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0928. Min Range: -5.0928
Max Act: 4.7803. Min Act: -0.1700
Data Index: 5652902 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0928. Min Range: -5.0928
Max Act: 4.7803. Min Act: -0.1700
Data Index: 3775457 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0928. Min Range: -5.0928
Max Act: 4.7803. Min Act: -0.1700
Data Index: 7466226 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0928. Min Range: -5.0928
Max Act: 4.7491. Min Act: -0.1700
Data Index: 3246668 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0928. Min Range: -5.0928
Max Act: 4.7491. Min Act: -0.1700
Data Index: 2541323 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0928. Min Range: -5.0928
Max Act: 4.7491. Min Act: -0.1700
Data Index: 2530278 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0928. Min Range: -5.0928
Max Act: 4.7491. Min Act: -0.1700
Data Index: 4585831 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #19