Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3884 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8498. Min Range: -5.8498
Max Act: 5.8498. Min Act: -0.1700
Data Index: 8327813 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8498. Min Range: -5.8498
Max Act: 5.5685. Min Act: -0.1700
Data Index: 2335802 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8498. Min Range: -5.8498
Max Act: 5.4748. Min Act: -0.1700
Data Index: 1602568 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8498. Min Range: -5.8498
Max Act: 5.4435. Min Act: -0.1700
Data Index: 3026150 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8498. Min Range: -5.8498
Max Act: 5.4123. Min Act: -0.1700
Data Index: 2335803 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8498. Min Range: -5.8498
Max Act: 5.3810. Min Act: -0.1700
Data Index: 5789129 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8498. Min Range: -5.8498
Max Act: 5.3810. Min Act: -0.1700
Data Index: 7588023 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8498. Min Range: -5.8498
Max Act: 5.3185. Min Act: -0.1700
Data Index: 1888104 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8498. Min Range: -5.8498
Max Act: 5.2873. Min Act: -0.1700
Data Index: 8005678 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8498. Min Range: -5.8498
Max Act: 5.2560. Min Act: -0.1700
Data Index: 4541148 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8498. Min Range: -5.8498
Max Act: 5.2560. Min Act: -0.1700
Data Index: 7808033 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8498. Min Range: -5.8498
Max Act: 5.1310. Min Act: -0.1700
Data Index: 7230243 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8498. Min Range: -5.8498
Max Act: 5.1310. Min Act: -0.1700
Data Index: 5819845 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8498. Min Range: -5.8498
Max Act: 5.0998. Min Act: -0.1700
Data Index: 7380742 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8498. Min Range: -5.8498
Max Act: 5.1310. Min Act: -0.1700
Data Index: 645422 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8498. Min Range: -5.8498
Max Act: 5.1623. Min Act: -0.1700
Data Index: 4783554 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8498. Min Range: -5.8498
Max Act: 5.1310. Min Act: -0.1700
Data Index: 7269785 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8498. Min Range: -5.8498
Max Act: 5.0998. Min Act: -0.1700
Data Index: 7277307 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8498. Min Range: -5.8498
Max Act: 5.0998. Min Act: -0.1700
Data Index: 700592 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8498. Min Range: -5.8498
Max Act: 5.0685. Min Act: -0.1700
Data Index: 5317815 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #19