Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3171 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7618. Min Range: -5.7618
Max Act: 5.7618. Min Act: -0.1700
Data Index: 136554 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7618. Min Range: -5.7618
Max Act: 5.7618. Min Act: -0.1700
Data Index: 3813808 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7618. Min Range: -5.7618
Max Act: 5.5743. Min Act: -0.1700
Data Index: 6786940 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7618. Min Range: -5.7618
Max Act: 5.5431. Min Act: -0.1700
Data Index: 6527213 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7618. Min Range: -5.7618
Max Act: 5.5118. Min Act: -0.1700
Data Index: 1174233 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7618. Min Range: -5.7618
Max Act: 5.5431. Min Act: -0.1700
Data Index: 6061687 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7618. Min Range: -5.7618
Max Act: 5.4806. Min Act: -0.1700
Data Index: 4007947 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7618. Min Range: -5.7618
Max Act: 5.4181. Min Act: -0.1700
Data Index: 3952049 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7618. Min Range: -5.7618
Max Act: 5.4181. Min Act: -0.1700
Data Index: 2735944 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7618. Min Range: -5.7618
Max Act: 5.3868. Min Act: -0.1700
Data Index: 88591 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7618. Min Range: -5.7618
Max Act: 5.4181. Min Act: -0.1700
Data Index: 5360670 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7618. Min Range: -5.7618
Max Act: 5.4181. Min Act: -0.1700
Data Index: 113071 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7618. Min Range: -5.7618
Max Act: 5.4181. Min Act: -0.1700
Data Index: 7692244 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7618. Min Range: -5.7618
Max Act: 5.3868. Min Act: -0.1700
Data Index: 6385641 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7618. Min Range: -5.7618
Max Act: 5.3556. Min Act: -0.1700
Data Index: 5383759 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7618. Min Range: -5.7618
Max Act: 5.3868. Min Act: -0.1700
Data Index: 1031639 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7618. Min Range: -5.7618
Max Act: 5.3556. Min Act: -0.1700
Data Index: 6889314 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7618. Min Range: -5.7618
Max Act: 5.3868. Min Act: -0.1700
Data Index: 5966840 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7618. Min Range: -5.7618
Max Act: 5.3556. Min Act: -0.1700
Data Index: 161812 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7618. Min Range: -5.7618
Max Act: 5.3556. Min Act: -0.1700
Data Index: 3480020 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #19