Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3328 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7125. Min Range: -7.7125
Max Act: 7.7125. Min Act: -0.1700
Data Index: 2757708 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7125. Min Range: -7.7125
Max Act: 7.3687. Min Act: -0.1700
Data Index: 4612268 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7125. Min Range: -7.7125
Max Act: 7.2125. Min Act: -0.1700
Data Index: 5547382 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7125. Min Range: -7.7125
Max Act: 7.1812. Min Act: -0.1700
Data Index: 2230705 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7125. Min Range: -7.7125
Max Act: 7.1500. Min Act: -0.1700
Data Index: 8354734 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7125. Min Range: -7.7125
Max Act: 7.0875. Min Act: -0.1700
Data Index: 5657669 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7125. Min Range: -7.7125
Max Act: 7.0250. Min Act: -0.1700
Data Index: 2003966 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7125. Min Range: -7.7125
Max Act: 6.9937. Min Act: -0.1700
Data Index: 8397516 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7125. Min Range: -7.7125
Max Act: 6.9625. Min Act: -0.1700
Data Index: 3960632 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7125. Min Range: -7.7125
Max Act: 6.9312. Min Act: -0.1700
Data Index: 7026730 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7125. Min Range: -7.7125
Max Act: 6.9000. Min Act: -0.1700
Data Index: 5285506 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7125. Min Range: -7.7125
Max Act: 6.9312. Min Act: -0.1700
Data Index: 3021761 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7125. Min Range: -7.7125
Max Act: 6.8062. Min Act: -0.1700
Data Index: 528577 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7125. Min Range: -7.7125
Max Act: 6.7750. Min Act: -0.1700
Data Index: 4773328 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7125. Min Range: -7.7125
Max Act: 6.7437. Min Act: -0.1700
Data Index: 1639045 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7125. Min Range: -7.7125
Max Act: 6.7437. Min Act: -0.1700
Data Index: 4451508 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7125. Min Range: -7.7125
Max Act: 6.6812. Min Act: -0.1700
Data Index: 5958812 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7125. Min Range: -7.7125
Max Act: 6.6187. Min Act: -0.1700
Data Index: 2279508 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7125. Min Range: -7.7125
Max Act: 6.6500. Min Act: -0.1700
Data Index: 453133 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7125. Min Range: -7.7125
Max Act: 6.5562. Min Act: -0.1700
Data Index: 7726511 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #19