Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3107 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8131. Min Range: -5.8131
Max Act: 5.8131. Min Act: -0.1700
Data Index: 3406308 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8131. Min Range: -5.8131
Max Act: 5.4069. Min Act: -0.1700
Data Index: 1283484 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8131. Min Range: -5.8131
Max Act: 5.4069. Min Act: -0.1700
Data Index: 4882857 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8131. Min Range: -5.8131
Max Act: 5.3444. Min Act: -0.1700
Data Index: 4016025 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8131. Min Range: -5.8131
Max Act: 5.3131. Min Act: -0.1700
Data Index: 3941883 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8131. Min Range: -5.8131
Max Act: 5.3131. Min Act: -0.1700
Data Index: 5120848 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8131. Min Range: -5.8131
Max Act: 5.2819. Min Act: -0.1700
Data Index: 6470289 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8131. Min Range: -5.8131
Max Act: 5.2819. Min Act: -0.1700
Data Index: 1221354 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8131. Min Range: -5.8131
Max Act: 5.2506. Min Act: -0.1700
Data Index: 2762303 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8131. Min Range: -5.8131
Max Act: 5.2194. Min Act: -0.1700
Data Index: 4841162 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8131. Min Range: -5.8131
Max Act: 5.2819. Min Act: -0.1700
Data Index: 1698931 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8131. Min Range: -5.8131
Max Act: 5.1569. Min Act: -0.1700
Data Index: 1399180 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8131. Min Range: -5.8131
Max Act: 5.1569. Min Act: -0.1700
Data Index: 8143194 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8131. Min Range: -5.8131
Max Act: 5.1569. Min Act: -0.1700
Data Index: 2994752 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8131. Min Range: -5.8131
Max Act: 5.0944. Min Act: -0.1700
Data Index: 2437265 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8131. Min Range: -5.8131
Max Act: 5.0944. Min Act: -0.1700
Data Index: 2995616 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8131. Min Range: -5.8131
Max Act: 5.0944. Min Act: -0.1700
Data Index: 8028843 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8131. Min Range: -5.8131
Max Act: 5.0944. Min Act: -0.1700
Data Index: 879574 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8131. Min Range: -5.8131
Max Act: 5.0631. Min Act: -0.1700
Data Index: 5577700 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8131. Min Range: -5.8131
Max Act: 5.0631. Min Act: -0.1700
Data Index: 2856165 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #19