Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2170 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1710. Min Range: -5.1710
Max Act: 5.1710. Min Act: -0.1700
Data Index: 3214679 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1710. Min Range: -5.1710
Max Act: 5.1710. Min Act: -0.1700
Data Index: 6647596 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1710. Min Range: -5.1710
Max Act: 5.1397. Min Act: -0.1700
Data Index: 3716040 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1710. Min Range: -5.1710
Max Act: 5.1085. Min Act: -0.1700
Data Index: 6319206 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1710. Min Range: -5.1710
Max Act: 5.1085. Min Act: -0.1700
Data Index: 6605011 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1710. Min Range: -5.1710
Max Act: 5.0772. Min Act: -0.1700
Data Index: 3952782 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1710. Min Range: -5.1710
Max Act: 5.0460. Min Act: -0.1700
Data Index: 6210554 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1710. Min Range: -5.1710
Max Act: 5.0460. Min Act: -0.1700
Data Index: 8469868 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1710. Min Range: -5.1710
Max Act: 5.0460. Min Act: -0.1700
Data Index: 2806535 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1710. Min Range: -5.1710
Max Act: 5.0460. Min Act: -0.1700
Data Index: 6533779 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1710. Min Range: -5.1710
Max Act: 5.0147. Min Act: -0.1700
Data Index: 2505959 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1710. Min Range: -5.1710
Max Act: 5.0147. Min Act: -0.1700
Data Index: 6647586 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1710. Min Range: -5.1710
Max Act: 5.0147. Min Act: -0.1700
Data Index: 6319197 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1710. Min Range: -5.1710
Max Act: 5.0147. Min Act: -0.1700
Data Index: 6319196 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1710. Min Range: -5.1710
Max Act: 5.0147. Min Act: -0.1700
Data Index: 6319210 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1710. Min Range: -5.1710
Max Act: 5.0147. Min Act: -0.1700
Data Index: 2325705 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1710. Min Range: -5.1710
Max Act: 4.9835. Min Act: -0.1700
Data Index: 6473441 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1710. Min Range: -5.1710
Max Act: 4.9835. Min Act: -0.1700
Data Index: 4740421 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1710. Min Range: -5.1710
Max Act: 4.9835. Min Act: -0.1700
Data Index: 6647594 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1710. Min Range: -5.1710
Max Act: 4.9522. Min Act: -0.1700
Data Index: 1704584 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #19