Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4917 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7119. Min Range: -6.7119
Max Act: 6.7119. Min Act: -0.1700
Data Index: 7661884 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7119. Min Range: -6.7119
Max Act: 6.4306. Min Act: -0.1700
Data Index: 5171376 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7119. Min Range: -6.7119
Max Act: 6.3994. Min Act: -0.1700
Data Index: 7329092 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7119. Min Range: -6.7119
Max Act: 6.3056. Min Act: -0.1700
Data Index: 612361 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7119. Min Range: -6.7119
Max Act: 6.1494. Min Act: -0.1700
Data Index: 5217281 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7119. Min Range: -6.7119
Max Act: 6.0869. Min Act: -0.1700
Data Index: 7087139 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7119. Min Range: -6.7119
Max Act: 6.0869. Min Act: -0.1700
Data Index: 7126706 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7119. Min Range: -6.7119
Max Act: 6.1181. Min Act: -0.1700
Data Index: 331662 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7119. Min Range: -6.7119
Max Act: 6.1181. Min Act: -0.1700
Data Index: 5867550 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7119. Min Range: -6.7119
Max Act: 6.0556. Min Act: -0.1700
Data Index: 1929417 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7119. Min Range: -6.7119
Max Act: 6.0556. Min Act: -0.1700
Data Index: 6813638 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7119. Min Range: -6.7119
Max Act: 6.0244. Min Act: -0.1700
Data Index: 4151461 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7119. Min Range: -6.7119
Max Act: 5.9931. Min Act: -0.1700
Data Index: 8038404 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7119. Min Range: -6.7119
Max Act: 5.9619. Min Act: -0.1700
Data Index: 1222321 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7119. Min Range: -6.7119
Max Act: 5.9619. Min Act: -0.1700
Data Index: 2818427 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7119. Min Range: -6.7119
Max Act: 5.9306. Min Act: -0.1700
Data Index: 6832333 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7119. Min Range: -6.7119
Max Act: 5.9306. Min Act: -0.1700
Data Index: 5895827 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7119. Min Range: -6.7119
Max Act: 5.8994. Min Act: -0.1700
Data Index: 3670141 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7119. Min Range: -6.7119
Max Act: 5.9306. Min Act: -0.1700
Data Index: 807439 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7119. Min Range: -6.7119
Max Act: 5.8994. Min Act: -0.1700
Data Index: 54122 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #19