Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5085 in Layer 41
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5037. Min Range: -7.5037
Max Act: 7.5037. Min Act: -0.1700
Data Index: 4777768 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5037. Min Range: -7.5037
Max Act: 7.2537. Min Act: -0.1700
Data Index: 7964574 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5037. Min Range: -7.5037
Max Act: 7.1912. Min Act: -0.1700
Data Index: 4200548 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5037. Min Range: -7.5037
Max Act: 7.1287. Min Act: -0.1700
Data Index: 86273 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5037. Min Range: -7.5037
Max Act: 7.0662. Min Act: -0.1700
Data Index: 834430 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5037. Min Range: -7.5037
Max Act: 7.0662. Min Act: -0.1700
Data Index: 7728488 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5037. Min Range: -7.5037
Max Act: 7.0975. Min Act: -0.1700
Data Index: 6730819 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5037. Min Range: -7.5037
Max Act: 7.0350. Min Act: -0.1700
Data Index: 1448093 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5037. Min Range: -7.5037
Max Act: 7.0350. Min Act: -0.1700
Data Index: 5356403 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5037. Min Range: -7.5037
Max Act: 7.0037. Min Act: -0.1700
Data Index: 8669751 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5037. Min Range: -7.5037
Max Act: 6.9725. Min Act: -0.1700
Data Index: 8515082 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5037. Min Range: -7.5037
Max Act: 6.9100. Min Act: -0.1700
Data Index: 6084972 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5037. Min Range: -7.5037
Max Act: 6.8787. Min Act: -0.1700
Data Index: 7274441 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5037. Min Range: -7.5037
Max Act: 6.8787. Min Act: -0.1700
Data Index: 6371470 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5037. Min Range: -7.5037
Max Act: 6.8475. Min Act: -0.1700
Data Index: 5756306 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5037. Min Range: -7.5037
Max Act: 6.8475. Min Act: -0.1700
Data Index: 6197677 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5037. Min Range: -7.5037
Max Act: 6.8162. Min Act: -0.1700
Data Index: 6550991 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5037. Min Range: -7.5037
Max Act: 6.8475. Min Act: -0.1700
Data Index: 1783346 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5037. Min Range: -7.5037
Max Act: 6.8475. Min Act: -0.1700
Data Index: 7324928 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5037. Min Range: -7.5037
Max Act: 6.8162. Min Act: -0.1700
Data Index: 1371227 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #19