Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2680 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0921. Min Range: -5.0921
Max Act: 5.0921. Min Act: -0.1700
Data Index: 4189361 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0921. Min Range: -5.0921
Max Act: 5.0296. Min Act: -0.1700
Data Index: 1531625 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0921. Min Range: -5.0921
Max Act: 4.9984. Min Act: -0.1700
Data Index: 7869077 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0921. Min Range: -5.0921
Max Act: 4.9671. Min Act: -0.1700
Data Index: 4434506 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0921. Min Range: -5.0921
Max Act: 4.9359. Min Act: -0.1700
Data Index: 3107015 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0921. Min Range: -5.0921
Max Act: 4.9359. Min Act: -0.1700
Data Index: 2437752 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0921. Min Range: -5.0921
Max Act: 4.9671. Min Act: -0.1700
Data Index: 6725605 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0921. Min Range: -5.0921
Max Act: 4.9046. Min Act: -0.1700
Data Index: 823092 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0921. Min Range: -5.0921
Max Act: 4.9046. Min Act: -0.1700
Data Index: 181146 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0921. Min Range: -5.0921
Max Act: 4.8734. Min Act: -0.1700
Data Index: 5106386 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0921. Min Range: -5.0921
Max Act: 4.8421. Min Act: -0.1700
Data Index: 428552 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0921. Min Range: -5.0921
Max Act: 4.8421. Min Act: -0.1700
Data Index: 3193030 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0921. Min Range: -5.0921
Max Act: 4.8109. Min Act: -0.1700
Data Index: 3481000 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0921. Min Range: -5.0921
Max Act: 4.7796. Min Act: -0.1700
Data Index: 6799287 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0921. Min Range: -5.0921
Max Act: 4.7484. Min Act: -0.1700
Data Index: 6222698 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0921. Min Range: -5.0921
Max Act: 4.7484. Min Act: -0.1700
Data Index: 2042247 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0921. Min Range: -5.0921
Max Act: 4.7484. Min Act: -0.1700
Data Index: 5862302 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0921. Min Range: -5.0921
Max Act: 4.7484. Min Act: -0.1700
Data Index: 8575749 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0921. Min Range: -5.0921
Max Act: 4.7171. Min Act: -0.1700
Data Index: 3185585 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0921. Min Range: -5.0921
Max Act: 4.7171. Min Act: -0.1700
Data Index: 6776609 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #19