Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3617 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8062. Min Range: -7.8062
Max Act: 7.8062. Min Act: -0.1700
Data Index: 8119534 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8062. Min Range: -7.8062
Max Act: 7.8062. Min Act: -0.1700
Data Index: 5263935 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8062. Min Range: -7.8062
Max Act: 7.5562. Min Act: -0.1700
Data Index: 7163811 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8062. Min Range: -7.8062
Max Act: 7.4937. Min Act: -0.1700
Data Index: 5263936 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8062. Min Range: -7.8062
Max Act: 7.4937. Min Act: -0.1700
Data Index: 7290444 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8062. Min Range: -7.8062
Max Act: 7.4312. Min Act: -0.1700
Data Index: 3254976 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8062. Min Range: -7.8062
Max Act: 7.3687. Min Act: -0.1700
Data Index: 5272022 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8062. Min Range: -7.8062
Max Act: 7.3687. Min Act: -0.1700
Data Index: 1880094 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8062. Min Range: -7.8062
Max Act: 7.3687. Min Act: -0.1700
Data Index: 7116887 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8062. Min Range: -7.8062
Max Act: 7.4312. Min Act: -0.1700
Data Index: 5263937 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8062. Min Range: -7.8062
Max Act: 7.3062. Min Act: -0.1700
Data Index: 2996163 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8062. Min Range: -7.8062
Max Act: 7.2437. Min Act: -0.1700
Data Index: 46357 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8062. Min Range: -7.8062
Max Act: 7.3062. Min Act: -0.1700
Data Index: 4774142 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8062. Min Range: -7.8062
Max Act: 7.2437. Min Act: -0.1700
Data Index: 1301344 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8062. Min Range: -7.8062
Max Act: 7.2437. Min Act: -0.1700
Data Index: 3636206 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8062. Min Range: -7.8062
Max Act: 7.3062. Min Act: -0.1700
Data Index: 421490 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8062. Min Range: -7.8062
Max Act: 7.1812. Min Act: -0.1700
Data Index: 6549632 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8062. Min Range: -7.8062
Max Act: 7.2437. Min Act: -0.1700
Data Index: 5515831 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8062. Min Range: -7.8062
Max Act: 7.2437. Min Act: -0.1700
Data Index: 5263938 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8062. Min Range: -7.8062
Max Act: 7.1812. Min Act: -0.1700
Data Index: 1975600 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #19