Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5268 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7201. Min Range: -5.7201
Max Act: 5.7201. Min Act: -0.1700
Data Index: 4196704 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7201. Min Range: -5.7201
Max Act: 5.6576. Min Act: -0.1700
Data Index: 1187278 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7201. Min Range: -5.7201
Max Act: 5.6264. Min Act: -0.1700
Data Index: 2058121 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7201. Min Range: -5.7201
Max Act: 5.5639. Min Act: -0.1700
Data Index: 8770255 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7201. Min Range: -5.7201
Max Act: 5.5014. Min Act: -0.1700
Data Index: 5331608 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7201. Min Range: -5.7201
Max Act: 5.5014. Min Act: -0.1700
Data Index: 815318 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7201. Min Range: -5.7201
Max Act: 5.5326. Min Act: -0.1700
Data Index: 4151917 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7201. Min Range: -5.7201
Max Act: 5.5326. Min Act: -0.1700
Data Index: 4911057 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7201. Min Range: -5.7201
Max Act: 5.5014. Min Act: -0.1700
Data Index: 5855999 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7201. Min Range: -5.7201
Max Act: 5.4701. Min Act: -0.1700
Data Index: 4550236 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7201. Min Range: -5.7201
Max Act: 5.4701. Min Act: -0.1700
Data Index: 5955141 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7201. Min Range: -5.7201
Max Act: 5.4076. Min Act: -0.1700
Data Index: 6574859 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7201. Min Range: -5.7201
Max Act: 5.3764. Min Act: -0.1700
Data Index: 3179040 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7201. Min Range: -5.7201
Max Act: 5.3764. Min Act: -0.1700
Data Index: 6734426 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7201. Min Range: -5.7201
Max Act: 5.4076. Min Act: -0.1700
Data Index: 3054956 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7201. Min Range: -5.7201
Max Act: 5.3764. Min Act: -0.1700
Data Index: 7358381 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7201. Min Range: -5.7201
Max Act: 5.3451. Min Act: -0.1700
Data Index: 3586690 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7201. Min Range: -5.7201
Max Act: 5.3764. Min Act: -0.1700
Data Index: 7276416 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7201. Min Range: -5.7201
Max Act: 5.3764. Min Act: -0.1700
Data Index: 6510206 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7201. Min Range: -5.7201
Max Act: 5.3764. Min Act: -0.1700
Data Index: 2932318 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #19