Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4052 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.0454. Min Range: -9.0454
Max Act: 9.0454. Min Act: -0.1700
Data Index: 321260 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.0454. Min Range: -9.0454
Max Act: 8.5454. Min Act: -0.1700
Data Index: 4664437 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.0454. Min Range: -9.0454
Max Act: 8.3579. Min Act: -0.1700
Data Index: 2478950 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.0454. Min Range: -9.0454
Max Act: 8.2954. Min Act: -0.1700
Data Index: 5040993 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.0454. Min Range: -9.0454
Max Act: 8.2954. Min Act: -0.1700
Data Index: 7899253 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.0454. Min Range: -9.0454
Max Act: 8.1079. Min Act: -0.1700
Data Index: 6131230 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.0454. Min Range: -9.0454
Max Act: 8.1079. Min Act: -0.1700
Data Index: 8372134 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.0454. Min Range: -9.0454
Max Act: 8.1079. Min Act: -0.1700
Data Index: 4982135 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.0454. Min Range: -9.0454
Max Act: 8.0454. Min Act: -0.1700
Data Index: 3996505 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.0454. Min Range: -9.0454
Max Act: 8.0454. Min Act: -0.1700
Data Index: 7043449 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.0454. Min Range: -9.0454
Max Act: 8.0454. Min Act: -0.1700
Data Index: 7654072 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.0454. Min Range: -9.0454
Max Act: 8.0454. Min Act: -0.1700
Data Index: 129384 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.0454. Min Range: -9.0454
Max Act: 8.0454. Min Act: -0.1700
Data Index: 5523071 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.0454. Min Range: -9.0454
Max Act: 8.0454. Min Act: -0.1700
Data Index: 7683037 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.0454. Min Range: -9.0454
Max Act: 7.9829. Min Act: -0.1700
Data Index: 294106 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.0454. Min Range: -9.0454
Max Act: 7.9204. Min Act: -0.1700
Data Index: 4601183 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.0454. Min Range: -9.0454
Max Act: 7.9204. Min Act: -0.1700
Data Index: 7575222 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.0454. Min Range: -9.0454
Max Act: 7.8579. Min Act: -0.1700
Data Index: 5196427 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.0454. Min Range: -9.0454
Max Act: 7.8579. Min Act: -0.1700
Data Index: 8072461 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.0454. Min Range: -9.0454
Max Act: 7.7954. Min Act: -0.1700
Data Index: 1970176 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #19