Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 280 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3116. Min Range: -6.3116
Max Act: 6.3116. Min Act: -0.1699
Data Index: 8074754 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3116. Min Range: -6.3116
Max Act: 6.0303. Min Act: -0.1700
Data Index: 2975467 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3116. Min Range: -6.3116
Max Act: 5.9678. Min Act: -0.1700
Data Index: 5352186 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3116. Min Range: -6.3116
Max Act: 5.9678. Min Act: -0.1700
Data Index: 7381731 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3116. Min Range: -6.3116
Max Act: 5.9366. Min Act: -0.1699
Data Index: 2180118 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3116. Min Range: -6.3116
Max Act: 5.9366. Min Act: -0.1700
Data Index: 351328 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3116. Min Range: -6.3116
Max Act: 5.9053. Min Act: -0.1700
Data Index: 4624527 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3116. Min Range: -6.3116
Max Act: 5.9053. Min Act: -0.1700
Data Index: 4872673 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3116. Min Range: -6.3116
Max Act: 5.8741. Min Act: -0.1700
Data Index: 2090405 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3116. Min Range: -6.3116
Max Act: 5.8741. Min Act: -0.1700
Data Index: 1522897 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3116. Min Range: -6.3116
Max Act: 5.8116. Min Act: -0.1700
Data Index: 4460990 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3116. Min Range: -6.3116
Max Act: 5.7803. Min Act: -0.1700
Data Index: 4401584 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3116. Min Range: -6.3116
Max Act: 5.7491. Min Act: -0.1700
Data Index: 5598511 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3116. Min Range: -6.3116
Max Act: 5.7491. Min Act: -0.1700
Data Index: 192545 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3116. Min Range: -6.3116
Max Act: 5.7491. Min Act: -0.1700
Data Index: 2269890 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3116. Min Range: -6.3116
Max Act: 5.7491. Min Act: -0.1700
Data Index: 6603382 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3116. Min Range: -6.3116
Max Act: 5.7491. Min Act: -0.1700
Data Index: 2895328 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3116. Min Range: -6.3116
Max Act: 5.7491. Min Act: -0.1700
Data Index: 2353508 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3116. Min Range: -6.3116
Max Act: 5.7178. Min Act: -0.1700
Data Index: 7145076 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3116. Min Range: -6.3116
Max Act: 5.6866. Min Act: -0.1700
Data Index: 1052130 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #19