Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1267 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.6911. Min Range: -5.6911
Max Act: 5.6911. Min Act: -0.1700
Data Index: 6678156 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6911. Min Range: -5.6911
Max Act: 5.5973. Min Act: -0.1700
Data Index: 5232801 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6911. Min Range: -5.6911
Max Act: 5.5036. Min Act: -0.1700
Data Index: 6948071 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6911. Min Range: -5.6911
Max Act: 5.5661. Min Act: -0.1700
Data Index: 4103353 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6911. Min Range: -5.6911
Max Act: 5.4723. Min Act: -0.1700
Data Index: 2264467 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6911. Min Range: -5.6911
Max Act: 5.4411. Min Act: -0.1700
Data Index: 6605947 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6911. Min Range: -5.6911
Max Act: 5.4098. Min Act: -0.1700
Data Index: 1265375 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6911. Min Range: -5.6911
Max Act: 5.3786. Min Act: -0.1700
Data Index: 1372001 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6911. Min Range: -5.6911
Max Act: 5.3786. Min Act: -0.1700
Data Index: 223267 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6911. Min Range: -5.6911
Max Act: 5.3786. Min Act: -0.1700
Data Index: 1862724 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6911. Min Range: -5.6911
Max Act: 5.3786. Min Act: -0.1700
Data Index: 5230622 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6911. Min Range: -5.6911
Max Act: 5.3161. Min Act: -0.1700
Data Index: 6153258 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6911. Min Range: -5.6911
Max Act: 5.2848. Min Act: -0.1700
Data Index: 51476 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6911. Min Range: -5.6911
Max Act: 5.2848. Min Act: -0.1700
Data Index: 1947644 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6911. Min Range: -5.6911
Max Act: 5.2848. Min Act: -0.1700
Data Index: 8792671 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6911. Min Range: -5.6911
Max Act: 5.2848. Min Act: -0.1700
Data Index: 8229028 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6911. Min Range: -5.6911
Max Act: 5.2848. Min Act: -0.1700
Data Index: 4816706 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6911. Min Range: -5.6911
Max Act: 5.3161. Min Act: -0.1700
Data Index: 5250780 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6911. Min Range: -5.6911
Max Act: 5.2536. Min Act: -0.1700
Data Index: 5351115 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6911. Min Range: -5.6911
Max Act: 5.2536. Min Act: -0.1700
Data Index: 645628 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #19