Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1161 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.0858. Min Range: -6.0858
Max Act: 6.0858. Min Act: -0.1700
Data Index: 2001932 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0858. Min Range: -6.0858
Max Act: 6.0858. Min Act: -0.1700
Data Index: 7746832 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0858. Min Range: -6.0858
Max Act: 6.0545. Min Act: -0.1700
Data Index: 3130214 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0858. Min Range: -6.0858
Max Act: 6.0233. Min Act: -0.1700
Data Index: 1360765 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0858. Min Range: -6.0858
Max Act: 6.0233. Min Act: -0.1700
Data Index: 4723322 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0858. Min Range: -6.0858
Max Act: 6.0233. Min Act: -0.1700
Data Index: 5863926 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0858. Min Range: -6.0858
Max Act: 5.9920. Min Act: -0.1700
Data Index: 625836 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0858. Min Range: -6.0858
Max Act: 5.9295. Min Act: -0.1700
Data Index: 6051761 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0858. Min Range: -6.0858
Max Act: 5.9608. Min Act: -0.1700
Data Index: 6826298 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0858. Min Range: -6.0858
Max Act: 5.9295. Min Act: -0.1700
Data Index: 2136738 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0858. Min Range: -6.0858
Max Act: 5.8670. Min Act: -0.1700
Data Index: 2902183 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0858. Min Range: -6.0858
Max Act: 5.8670. Min Act: -0.1700
Data Index: 8370060 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0858. Min Range: -6.0858
Max Act: 5.8670. Min Act: -0.1700
Data Index: 7032329 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0858. Min Range: -6.0858
Max Act: 5.8358. Min Act: -0.1700
Data Index: 16499 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0858. Min Range: -6.0858
Max Act: 5.8358. Min Act: -0.1700
Data Index: 3208297 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0858. Min Range: -6.0858
Max Act: 5.8358. Min Act: -0.1700
Data Index: 8753019 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0858. Min Range: -6.0858
Max Act: 5.8358. Min Act: -0.1700
Data Index: 5189221 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0858. Min Range: -6.0858
Max Act: 5.8045. Min Act: -0.1700
Data Index: 7969232 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0858. Min Range: -6.0858
Max Act: 5.8045. Min Act: -0.1700
Data Index: 2000910 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0858. Min Range: -6.0858
Max Act: 5.8045. Min Act: -0.1700
Data Index: 2701239 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #19