Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3450 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4114. Min Range: -7.4114
Max Act: 7.4114. Min Act: -0.1700
Data Index: 1866899 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4114. Min Range: -7.4114
Max Act: 6.9739. Min Act: -0.1700
Data Index: 2307662 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4114. Min Range: -7.4114
Max Act: 6.8489. Min Act: -0.1700
Data Index: 1458966 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4114. Min Range: -7.4114
Max Act: 6.7239. Min Act: -0.1700
Data Index: 8574083 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4114. Min Range: -7.4114
Max Act: 6.6927. Min Act: -0.1700
Data Index: 7677595 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4114. Min Range: -7.4114
Max Act: 6.6302. Min Act: -0.1700
Data Index: 5380125 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4114. Min Range: -7.4114
Max Act: 6.5989. Min Act: -0.1700
Data Index: 3807547 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4114. Min Range: -7.4114
Max Act: 6.5989. Min Act: -0.1700
Data Index: 7274374 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4114. Min Range: -7.4114
Max Act: 6.5989. Min Act: -0.1700
Data Index: 7689141 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4114. Min Range: -7.4114
Max Act: 6.5989. Min Act: -0.1700
Data Index: 5651015 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4114. Min Range: -7.4114
Max Act: 6.5989. Min Act: -0.1700
Data Index: 1280982 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4114. Min Range: -7.4114
Max Act: 6.5989. Min Act: -0.1700
Data Index: 5076176 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4114. Min Range: -7.4114
Max Act: 6.5989. Min Act: -0.1700
Data Index: 3123960 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4114. Min Range: -7.4114
Max Act: 6.4739. Min Act: -0.1700
Data Index: 1023901 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4114. Min Range: -7.4114
Max Act: 6.5052. Min Act: -0.1700
Data Index: 3017875 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4114. Min Range: -7.4114
Max Act: 6.5052. Min Act: -0.1700
Data Index: 3215317 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4114. Min Range: -7.4114
Max Act: 6.4739. Min Act: -0.1700
Data Index: 107317 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4114. Min Range: -7.4114
Max Act: 6.4739. Min Act: -0.1700
Data Index: 8515066 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4114. Min Range: -7.4114
Max Act: 6.4427. Min Act: -0.1700
Data Index: 5632924 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4114. Min Range: -7.4114
Max Act: 6.4114. Min Act: -0.1700
Data Index: 490978 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #19