Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1904 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5125. Min Range: -7.5125
Max Act: 7.5125. Min Act: -0.1700
Data Index: 2999202 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5125. Min Range: -7.5125
Max Act: 7.4500. Min Act: -0.1700
Data Index: 2738283 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5125. Min Range: -7.5125
Max Act: 7.0750. Min Act: -0.1700
Data Index: 8567857 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5125. Min Range: -7.5125
Max Act: 7.0437. Min Act: -0.1700
Data Index: 4426398 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5125. Min Range: -7.5125
Max Act: 7.0125. Min Act: -0.1700
Data Index: 3508848 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5125. Min Range: -7.5125
Max Act: 6.9812. Min Act: -0.1700
Data Index: 913013 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5125. Min Range: -7.5125
Max Act: 6.9500. Min Act: -0.1700
Data Index: 6657804 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5125. Min Range: -7.5125
Max Act: 6.8875. Min Act: -0.1700
Data Index: 7556914 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5125. Min Range: -7.5125
Max Act: 6.8875. Min Act: -0.1700
Data Index: 2772234 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5125. Min Range: -7.5125
Max Act: 6.8875. Min Act: -0.1700
Data Index: 729069 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5125. Min Range: -7.5125
Max Act: 6.8875. Min Act: -0.1700
Data Index: 5461587 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5125. Min Range: -7.5125
Max Act: 6.8562. Min Act: -0.1700
Data Index: 3823985 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5125. Min Range: -7.5125
Max Act: 6.8250. Min Act: -0.1700
Data Index: 6563431 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5125. Min Range: -7.5125
Max Act: 6.7625. Min Act: -0.1700
Data Index: 150110 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5125. Min Range: -7.5125
Max Act: 6.8250. Min Act: -0.1700
Data Index: 5229764 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5125. Min Range: -7.5125
Max Act: 6.7625. Min Act: -0.1700
Data Index: 703697 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5125. Min Range: -7.5125
Max Act: 6.8250. Min Act: -0.1700
Data Index: 494380 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5125. Min Range: -7.5125
Max Act: 6.7625. Min Act: -0.1700
Data Index: 7576002 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5125. Min Range: -7.5125
Max Act: 6.7625. Min Act: -0.1700
Data Index: 143600 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5125. Min Range: -7.5125
Max Act: 6.7625. Min Act: -0.1700
Data Index: 6022563 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #19