Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5197 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.8332. Min Range: -8.8332
Max Act: 8.8332. Min Act: -0.1700
Data Index: 778275 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.8332. Min Range: -8.8332
Max Act: 8.7082. Min Act: -0.1700
Data Index: 1115039 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.8332. Min Range: -8.8332
Max Act: 8.7082. Min Act: -0.1700
Data Index: 1142252 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.8332. Min Range: -8.8332
Max Act: 8.5832. Min Act: -0.1700
Data Index: 7402281 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.8332. Min Range: -8.8332
Max Act: 8.5832. Min Act: -0.1700
Data Index: 3211257 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.8332. Min Range: -8.8332
Max Act: 8.4582. Min Act: -0.1700
Data Index: 2812518 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.8332. Min Range: -8.8332
Max Act: 8.4582. Min Act: -0.1700
Data Index: 8500840 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.8332. Min Range: -8.8332
Max Act: 8.4582. Min Act: -0.1700
Data Index: 3294963 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.8332. Min Range: -8.8332
Max Act: 8.3957. Min Act: -0.1700
Data Index: 1773506 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.8332. Min Range: -8.8332
Max Act: 8.3645. Min Act: -0.1700
Data Index: 2857935 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.8332. Min Range: -8.8332
Max Act: 8.3332. Min Act: -0.1700
Data Index: 4629904 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.8332. Min Range: -8.8332
Max Act: 8.3332. Min Act: -0.1700
Data Index: 2228390 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.8332. Min Range: -8.8332
Max Act: 8.3020. Min Act: -0.1700
Data Index: 3569408 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.8332. Min Range: -8.8332
Max Act: 8.2395. Min Act: -0.1700
Data Index: 7454500 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.8332. Min Range: -8.8332
Max Act: 8.2395. Min Act: -0.1700
Data Index: 2190495 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.8332. Min Range: -8.8332
Max Act: 8.2395. Min Act: -0.1700
Data Index: 998719 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.8332. Min Range: -8.8332
Max Act: 8.1770. Min Act: -0.1700
Data Index: 8219381 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.8332. Min Range: -8.8332
Max Act: 8.2082. Min Act: -0.1700
Data Index: 6552471 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.8332. Min Range: -8.8332
Max Act: 8.2082. Min Act: -0.1700
Data Index: 1093462 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.8332. Min Range: -8.8332
Max Act: 8.1770. Min Act: -0.1700
Data Index: 7136088 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #19