Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5970 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4524. Min Range: -6.4524
Max Act: 6.4524. Min Act: -0.1700
Data Index: 6127859 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4524. Min Range: -6.4524
Max Act: 6.2337. Min Act: -0.1700
Data Index: 8559916 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4524. Min Range: -6.4524
Max Act: 6.0462. Min Act: -0.1700
Data Index: 8559906 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4524. Min Range: -6.4524
Max Act: 5.8587. Min Act: -0.1700
Data Index: 3422748 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4524. Min Range: -6.4524
Max Act: 5.8587. Min Act: -0.1700
Data Index: 4688754 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4524. Min Range: -6.4524
Max Act: 5.7649. Min Act: -0.1700
Data Index: 5083306 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4524. Min Range: -6.4524
Max Act: 5.7649. Min Act: -0.1700
Data Index: 1732056 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4524. Min Range: -6.4524
Max Act: 5.7337. Min Act: -0.1700
Data Index: 5330161 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4524. Min Range: -6.4524
Max Act: 5.7024. Min Act: -0.1700
Data Index: 6997821 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4524. Min Range: -6.4524
Max Act: 5.7024. Min Act: -0.1700
Data Index: 8169923 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4524. Min Range: -6.4524
Max Act: 5.6712. Min Act: -0.1700
Data Index: 1999954 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4524. Min Range: -6.4524
Max Act: 5.6399. Min Act: -0.1700
Data Index: 5047805 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4524. Min Range: -6.4524
Max Act: 5.6712. Min Act: -0.1700
Data Index: 4104785 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4524. Min Range: -6.4524
Max Act: 5.6087. Min Act: -0.1700
Data Index: 6776529 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4524. Min Range: -6.4524
Max Act: 5.6087. Min Act: -0.1700
Data Index: 6970264 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4524. Min Range: -6.4524
Max Act: 5.6087. Min Act: -0.1700
Data Index: 7756429 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4524. Min Range: -6.4524
Max Act: 5.6399. Min Act: -0.1700
Data Index: 4593176 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4524. Min Range: -6.4524
Max Act: 5.6087. Min Act: -0.1700
Data Index: 4283808 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4524. Min Range: -6.4524
Max Act: 5.6087. Min Act: -0.1700
Data Index: 6072144 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4524. Min Range: -6.4524
Max Act: 5.5774. Min Act: -0.1700
Data Index: 3564944 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #19