Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 68 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8003. Min Range: -5.8003
Max Act: 5.8003. Min Act: -0.1700
Data Index: 3957499 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8003. Min Range: -5.8003
Max Act: 5.7378. Min Act: -0.1700
Data Index: 7655096 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8003. Min Range: -5.8003
Max Act: 5.7065. Min Act: -0.1700
Data Index: 785615 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8003. Min Range: -5.8003
Max Act: 5.6440. Min Act: -0.1700
Data Index: 1180265 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8003. Min Range: -5.8003
Max Act: 5.6440. Min Act: -0.1700
Data Index: 292798 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8003. Min Range: -5.8003
Max Act: 5.6440. Min Act: -0.1700
Data Index: 3027117 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8003. Min Range: -5.8003
Max Act: 5.6128. Min Act: -0.1700
Data Index: 5208137 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8003. Min Range: -5.8003
Max Act: 5.6128. Min Act: -0.1700
Data Index: 8593267 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8003. Min Range: -5.8003
Max Act: 5.5815. Min Act: -0.1700
Data Index: 1679055 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8003. Min Range: -5.8003
Max Act: 5.5815. Min Act: -0.1700
Data Index: 5403387 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8003. Min Range: -5.8003
Max Act: 5.5815. Min Act: -0.1700
Data Index: 4549235 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8003. Min Range: -5.8003
Max Act: 5.5503. Min Act: -0.1700
Data Index: 8048758 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8003. Min Range: -5.8003
Max Act: 5.5503. Min Act: -0.1700
Data Index: 5867353 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8003. Min Range: -5.8003
Max Act: 5.5503. Min Act: -0.1700
Data Index: 5447691 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8003. Min Range: -5.8003
Max Act: 5.5503. Min Act: -0.1700
Data Index: 1701813 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8003. Min Range: -5.8003
Max Act: 5.5503. Min Act: -0.1700
Data Index: 4160307 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8003. Min Range: -5.8003
Max Act: 5.5503. Min Act: -0.1700
Data Index: 11531 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8003. Min Range: -5.8003
Max Act: 5.5503. Min Act: -0.1700
Data Index: 4884311 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8003. Min Range: -5.8003
Max Act: 5.5190. Min Act: -0.1700
Data Index: 4443618 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8003. Min Range: -5.8003
Max Act: 5.5190. Min Act: -0.1700
Data Index: 4611252 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #19