Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1666 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8981. Min Range: -4.8981
Max Act: 4.8981. Min Act: -0.1700
Data Index: 7584878 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8981. Min Range: -4.8981
Max Act: 4.7106. Min Act: -0.1700
Data Index: 8160814 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8981. Min Range: -4.8981
Max Act: 4.7106. Min Act: -0.1700
Data Index: 5893997 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8981. Min Range: -4.8981
Max Act: 4.6481. Min Act: -0.1700
Data Index: 3059743 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8981. Min Range: -4.8981
Max Act: 4.6481. Min Act: -0.1700
Data Index: 7168813 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8981. Min Range: -4.8981
Max Act: 4.6168. Min Act: -0.1700
Data Index: 8335533 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8981. Min Range: -4.8981
Max Act: 4.6168. Min Act: -0.1700
Data Index: 3184107 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8981. Min Range: -4.8981
Max Act: 4.6168. Min Act: -0.1700
Data Index: 2307772 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8981. Min Range: -4.8981
Max Act: 4.6481. Min Act: -0.1700
Data Index: 3351932 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8981. Min Range: -4.8981
Max Act: 4.5856. Min Act: -0.1700
Data Index: 3673851 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8981. Min Range: -4.8981
Max Act: 4.5543. Min Act: -0.1700
Data Index: 4110300 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8981. Min Range: -4.8981
Max Act: 4.5543. Min Act: -0.1700
Data Index: 3503985 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8981. Min Range: -4.8981
Max Act: 4.5543. Min Act: -0.1700
Data Index: 8353174 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8981. Min Range: -4.8981
Max Act: 4.5543. Min Act: -0.1700
Data Index: 8689354 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8981. Min Range: -4.8981
Max Act: 4.4918. Min Act: -0.1700
Data Index: 8007324 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8981. Min Range: -4.8981
Max Act: 4.5231. Min Act: -0.1700
Data Index: 6355974 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8981. Min Range: -4.8981
Max Act: 4.5231. Min Act: -0.1700
Data Index: 1737414 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8981. Min Range: -4.8981
Max Act: 4.5231. Min Act: -0.1700
Data Index: 8061 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8981. Min Range: -4.8981
Max Act: 4.5231. Min Act: -0.1700
Data Index: 2455309 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8981. Min Range: -4.8981
Max Act: 4.4918. Min Act: -0.1700
Data Index: 8286800 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #19