Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2748 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5471. Min Range: -6.5471
Max Act: 6.5471. Min Act: -0.1700
Data Index: 4270032 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5471. Min Range: -6.5471
Max Act: 6.2346. Min Act: -0.1700
Data Index: 4880456 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5471. Min Range: -6.5471
Max Act: 6.2034. Min Act: -0.1700
Data Index: 3144566 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5471. Min Range: -6.5471
Max Act: 6.0784. Min Act: -0.1700
Data Index: 55316 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5471. Min Range: -6.5471
Max Act: 6.0471. Min Act: -0.1700
Data Index: 5532451 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5471. Min Range: -6.5471
Max Act: 6.0784. Min Act: -0.1700
Data Index: 654695 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5471. Min Range: -6.5471
Max Act: 6.0471. Min Act: -0.1700
Data Index: 5159161 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5471. Min Range: -6.5471
Max Act: 5.9846. Min Act: -0.1700
Data Index: 4901286 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5471. Min Range: -6.5471
Max Act: 6.0159. Min Act: -0.1700
Data Index: 5666811 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5471. Min Range: -6.5471
Max Act: 5.9534. Min Act: -0.1700
Data Index: 648912 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5471. Min Range: -6.5471
Max Act: 5.9221. Min Act: -0.1700
Data Index: 8516008 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5471. Min Range: -6.5471
Max Act: 5.9221. Min Act: -0.1700
Data Index: 8175464 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5471. Min Range: -6.5471
Max Act: 5.9221. Min Act: -0.1700
Data Index: 5550018 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5471. Min Range: -6.5471
Max Act: 5.9534. Min Act: -0.1700
Data Index: 8215638 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5471. Min Range: -6.5471
Max Act: 5.9534. Min Act: -0.1700
Data Index: 83578 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5471. Min Range: -6.5471
Max Act: 5.8909. Min Act: -0.1700
Data Index: 3290352 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5471. Min Range: -6.5471
Max Act: 5.8909. Min Act: -0.1700
Data Index: 4534029 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5471. Min Range: -6.5471
Max Act: 5.9221. Min Act: -0.1700
Data Index: 6245302 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5471. Min Range: -6.5471
Max Act: 5.8909. Min Act: -0.1700
Data Index: 2578663 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5471. Min Range: -6.5471
Max Act: 5.8909. Min Act: -0.1700
Data Index: 1340640 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #19