Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4782 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0109. Min Range: -4.0109
Max Act: 4.0109. Min Act: -0.1700
Data Index: 8599371 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0109. Min Range: -4.0109
Max Act: 3.9484. Min Act: -0.1700
Data Index: 6948035 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0109. Min Range: -4.0109
Max Act: 3.9484. Min Act: -0.1700
Data Index: 8472324 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0109. Min Range: -4.0109
Max Act: 3.9171. Min Act: -0.1700
Data Index: 5255921 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0109. Min Range: -4.0109
Max Act: 3.9171. Min Act: -0.1700
Data Index: 4856215 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0109. Min Range: -4.0109
Max Act: 3.8858. Min Act: -0.1700
Data Index: 7322148 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0109. Min Range: -4.0109
Max Act: 3.8858. Min Act: -0.1700
Data Index: 7107658 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0109. Min Range: -4.0109
Max Act: 3.8546. Min Act: -0.1700
Data Index: 4920283 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0109. Min Range: -4.0109
Max Act: 3.8546. Min Act: -0.1700
Data Index: 8426451 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0109. Min Range: -4.0109
Max Act: 3.8233. Min Act: -0.1700
Data Index: 3627010 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0109. Min Range: -4.0109
Max Act: 3.8233. Min Act: -0.1700
Data Index: 4751326 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0109. Min Range: -4.0109
Max Act: 3.8233. Min Act: -0.1700
Data Index: 3336446 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0109. Min Range: -4.0109
Max Act: 3.8233. Min Act: -0.1700
Data Index: 1947238 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0109. Min Range: -4.0109
Max Act: 3.7920. Min Act: -0.1700
Data Index: 6237955 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0109. Min Range: -4.0109
Max Act: 3.7920. Min Act: -0.1700
Data Index: 1299418 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0109. Min Range: -4.0109
Max Act: 3.7920. Min Act: -0.1700
Data Index: 8798855 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0109. Min Range: -4.0109
Max Act: 3.7920. Min Act: -0.1700
Data Index: 222633 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0109. Min Range: -4.0109
Max Act: 3.7920. Min Act: -0.1700
Data Index: 6027939 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0109. Min Range: -4.0109
Max Act: 3.7607. Min Act: -0.1700
Data Index: 8342959 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0109. Min Range: -4.0109
Max Act: 3.7607. Min Act: -0.1700
Data Index: 5815589 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #19