Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2451 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3957. Min Range: -6.3957
Max Act: 6.3957. Min Act: -0.1700
Data Index: 7991986 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3957. Min Range: -6.3957
Max Act: 6.2707. Min Act: -0.1700
Data Index: 5741181 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3957. Min Range: -6.3957
Max Act: 6.2395. Min Act: -0.1700
Data Index: 4723805 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3957. Min Range: -6.3957
Max Act: 6.2395. Min Act: -0.1700
Data Index: 2561477 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3957. Min Range: -6.3957
Max Act: 6.1770. Min Act: -0.1700
Data Index: 2824794 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3957. Min Range: -6.3957
Max Act: 6.1457. Min Act: -0.1700
Data Index: 786944 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3957. Min Range: -6.3957
Max Act: 6.1457. Min Act: -0.1700
Data Index: 4265471 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3957. Min Range: -6.3957
Max Act: 6.1145. Min Act: -0.1700
Data Index: 560027 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3957. Min Range: -6.3957
Max Act: 6.1145. Min Act: -0.1700
Data Index: 79244 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3957. Min Range: -6.3957
Max Act: 6.0520. Min Act: -0.1700
Data Index: 6388959 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3957. Min Range: -6.3957
Max Act: 6.0832. Min Act: -0.1700
Data Index: 102866 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3957. Min Range: -6.3957
Max Act: 6.0832. Min Act: -0.1700
Data Index: 3295484 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3957. Min Range: -6.3957
Max Act: 6.0832. Min Act: -0.1700
Data Index: 8532939 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3957. Min Range: -6.3957
Max Act: 6.0832. Min Act: -0.1700
Data Index: 5528451 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3957. Min Range: -6.3957
Max Act: 6.0520. Min Act: -0.1700
Data Index: 3791547 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3957. Min Range: -6.3957
Max Act: 6.0520. Min Act: -0.1700
Data Index: 7126407 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3957. Min Range: -6.3957
Max Act: 6.0520. Min Act: -0.1700
Data Index: 5314757 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3957. Min Range: -6.3957
Max Act: 6.0207. Min Act: -0.1700
Data Index: 1971514 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3957. Min Range: -6.3957
Max Act: 6.0207. Min Act: -0.1700
Data Index: 686582 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3957. Min Range: -6.3957
Max Act: 6.0207. Min Act: -0.1700
Data Index: 3229057 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #19