Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 597 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4986. Min Range: -4.4986
Max Act: 4.4986. Min Act: -0.1700
Data Index: 1003518 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4986. Min Range: -4.4986
Max Act: 4.3735. Min Act: -0.1700
Data Index: 234744 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4986. Min Range: -4.4986
Max Act: 4.3110. Min Act: -0.1700
Data Index: 2538170 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4986. Min Range: -4.4986
Max Act: 4.1235. Min Act: -0.1700
Data Index: 7196994 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4986. Min Range: -4.4986
Max Act: 4.0923. Min Act: -0.1700
Data Index: 2538171 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4986. Min Range: -4.4986
Max Act: 4.0610. Min Act: -0.1700
Data Index: 7747625 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4986. Min Range: -4.4986
Max Act: 4.0923. Min Act: -0.1700
Data Index: 7660205 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4986. Min Range: -4.4986
Max Act: 4.0610. Min Act: -0.1700
Data Index: 6929458 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4986. Min Range: -4.4986
Max Act: 4.0297. Min Act: -0.1700
Data Index: 7845032 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4986. Min Range: -4.4986
Max Act: 3.9985. Min Act: -0.1700
Data Index: 2050059 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4986. Min Range: -4.4986
Max Act: 3.9985. Min Act: -0.1700
Data Index: 815826 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4986. Min Range: -4.4986
Max Act: 3.9985. Min Act: -0.1700
Data Index: 1392806 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4986. Min Range: -4.4986
Max Act: 3.9985. Min Act: -0.1700
Data Index: 1864979 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4986. Min Range: -4.4986
Max Act: 3.9985. Min Act: -0.1700
Data Index: 8697613 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4986. Min Range: -4.4986
Max Act: 3.9985. Min Act: -0.1700
Data Index: 2575217 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4986. Min Range: -4.4986
Max Act: 3.9672. Min Act: -0.1700
Data Index: 6184960 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4986. Min Range: -4.4986
Max Act: 3.9672. Min Act: -0.1700
Data Index: 2758946 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4986. Min Range: -4.4986
Max Act: 3.9672. Min Act: -0.1700
Data Index: 8561639 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4986. Min Range: -4.4986
Max Act: 3.9985. Min Act: -0.1700
Data Index: 2760249 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4986. Min Range: -4.4986
Max Act: 3.9672. Min Act: -0.1700
Data Index: 6406697 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #19