Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2564 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2104. Min Range: -6.2104
Max Act: 6.2104. Min Act: -0.1700
Data Index: 4408655 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2104. Min Range: -6.2104
Max Act: 6.0541. Min Act: -0.1700
Data Index: 6127345 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2104. Min Range: -6.2104
Max Act: 5.9916. Min Act: -0.1700
Data Index: 6127343 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2104. Min Range: -6.2104
Max Act: 5.8979. Min Act: -0.1700
Data Index: 5987119 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2104. Min Range: -6.2104
Max Act: 5.8354. Min Act: -0.1700
Data Index: 702350 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2104. Min Range: -6.2104
Max Act: 5.8041. Min Act: -0.1700
Data Index: 3219758 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2104. Min Range: -6.2104
Max Act: 5.7729. Min Act: -0.1700
Data Index: 7034876 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2104. Min Range: -6.2104
Max Act: 5.7729. Min Act: -0.1700
Data Index: 6092560 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2104. Min Range: -6.2104
Max Act: 5.7729. Min Act: -0.1700
Data Index: 1025851 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2104. Min Range: -6.2104
Max Act: 5.7416. Min Act: -0.1700
Data Index: 2031525 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2104. Min Range: -6.2104
Max Act: 5.7416. Min Act: -0.1700
Data Index: 7702476 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2104. Min Range: -6.2104
Max Act: 5.7416. Min Act: -0.1700
Data Index: 8310246 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2104. Min Range: -6.2104
Max Act: 5.7104. Min Act: -0.1700
Data Index: 6142349 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2104. Min Range: -6.2104
Max Act: 5.7104. Min Act: -0.1700
Data Index: 3823935 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2104. Min Range: -6.2104
Max Act: 5.7104. Min Act: -0.1700
Data Index: 812693 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2104. Min Range: -6.2104
Max Act: 5.7104. Min Act: -0.1700
Data Index: 917909 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2104. Min Range: -6.2104
Max Act: 5.7104. Min Act: -0.1700
Data Index: 5311661 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2104. Min Range: -6.2104
Max Act: 5.7104. Min Act: -0.1700
Data Index: 1233075 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2104. Min Range: -6.2104
Max Act: 5.6791. Min Act: -0.1700
Data Index: 5696392 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2104. Min Range: -6.2104
Max Act: 5.6791. Min Act: -0.1700
Data Index: 1227988 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #19