Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2612 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2031. Min Range: -6.2031
Max Act: 6.2031. Min Act: -0.1700
Data Index: 2754865 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2031. Min Range: -6.2031
Max Act: 6.2031. Min Act: -0.1700
Data Index: 7985988 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2031. Min Range: -6.2031
Max Act: 6.2031. Min Act: -0.1700
Data Index: 7985987 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2031. Min Range: -6.2031
Max Act: 6.2031. Min Act: -0.1700
Data Index: 8399278 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2031. Min Range: -6.2031
Max Act: 6.2031. Min Act: -0.1700
Data Index: 3418634 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2031. Min Range: -6.2031
Max Act: 5.9844. Min Act: -0.1700
Data Index: 7493328 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2031. Min Range: -6.2031
Max Act: 5.9531. Min Act: -0.1700
Data Index: 1335063 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2031. Min Range: -6.2031
Max Act: 5.9219. Min Act: -0.1700
Data Index: 5716141 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2031. Min Range: -6.2031
Max Act: 5.9531. Min Act: -0.1700
Data Index: 5155900 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2031. Min Range: -6.2031
Max Act: 5.9219. Min Act: -0.1700
Data Index: 4070614 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2031. Min Range: -6.2031
Max Act: 5.9219. Min Act: -0.1700
Data Index: 7829212 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2031. Min Range: -6.2031
Max Act: 5.8906. Min Act: -0.1700
Data Index: 6280821 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2031. Min Range: -6.2031
Max Act: 5.8906. Min Act: -0.1700
Data Index: 1386223 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2031. Min Range: -6.2031
Max Act: 5.8594. Min Act: -0.1700
Data Index: 5844251 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2031. Min Range: -6.2031
Max Act: 5.8281. Min Act: -0.1700
Data Index: 4956814 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2031. Min Range: -6.2031
Max Act: 5.8281. Min Act: -0.1700
Data Index: 2853368 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2031. Min Range: -6.2031
Max Act: 5.7656. Min Act: -0.1700
Data Index: 2504287 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2031. Min Range: -6.2031
Max Act: 5.7656. Min Act: -0.1700
Data Index: 7494873 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2031. Min Range: -6.2031
Max Act: 5.7344. Min Act: -0.1700
Data Index: 3954929 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2031. Min Range: -6.2031
Max Act: 5.7344. Min Act: -0.1700
Data Index: 7939940 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #19