Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2852 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4147. Min Range: -6.4147
Max Act: 6.4147. Min Act: -0.1700
Data Index: 4167281 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4147. Min Range: -6.4147
Max Act: 6.3209. Min Act: -0.1700
Data Index: 1630296 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4147. Min Range: -6.4147
Max Act: 6.2272. Min Act: -0.1700
Data Index: 364413 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4147. Min Range: -6.4147
Max Act: 6.1959. Min Act: -0.1700
Data Index: 537425 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4147. Min Range: -6.4147
Max Act: 6.1022. Min Act: -0.1700
Data Index: 2652790 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4147. Min Range: -6.4147
Max Act: 6.0397. Min Act: -0.1700
Data Index: 2699807 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4147. Min Range: -6.4147
Max Act: 6.0397. Min Act: -0.1700
Data Index: 1833845 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4147. Min Range: -6.4147
Max Act: 6.0397. Min Act: -0.1700
Data Index: 8317780 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4147. Min Range: -6.4147
Max Act: 6.0084. Min Act: -0.1700
Data Index: 6614673 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4147. Min Range: -6.4147
Max Act: 6.0084. Min Act: -0.1700
Data Index: 3081198 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4147. Min Range: -6.4147
Max Act: 5.9147. Min Act: -0.1700
Data Index: 8459556 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4147. Min Range: -6.4147
Max Act: 5.9147. Min Act: -0.1700
Data Index: 8536333 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4147. Min Range: -6.4147
Max Act: 5.9147. Min Act: -0.1700
Data Index: 2087758 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4147. Min Range: -6.4147
Max Act: 5.8834. Min Act: -0.1700
Data Index: 2038010 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4147. Min Range: -6.4147
Max Act: 5.8834. Min Act: -0.1700
Data Index: 2448610 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4147. Min Range: -6.4147
Max Act: 5.9147. Min Act: -0.1700
Data Index: 3395612 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4147. Min Range: -6.4147
Max Act: 5.8834. Min Act: -0.1700
Data Index: 5065045 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4147. Min Range: -6.4147
Max Act: 5.8522. Min Act: -0.1700
Data Index: 6308698 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4147. Min Range: -6.4147
Max Act: 5.8522. Min Act: -0.1700
Data Index: 460520 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4147. Min Range: -6.4147
Max Act: 5.8522. Min Act: -0.1700
Data Index: 4853367 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #19