Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3289 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9866. Min Range: -4.9866
Max Act: 4.9866. Min Act: -0.1700
Data Index: 6020609 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9866. Min Range: -4.9866
Max Act: 4.9866. Min Act: -0.1700
Data Index: 2381771 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9866. Min Range: -4.9866
Max Act: 4.9554. Min Act: -0.1700
Data Index: 3700865 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9866. Min Range: -4.9866
Max Act: 4.9554. Min Act: -0.1700
Data Index: 2652288 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9866. Min Range: -4.9866
Max Act: 4.9554. Min Act: -0.1700
Data Index: 6084833 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9866. Min Range: -4.9866
Max Act: 4.9554. Min Act: -0.1700
Data Index: 5306464 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9866. Min Range: -4.9866
Max Act: 4.9241. Min Act: -0.1700
Data Index: 7058943 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9866. Min Range: -4.9866
Max Act: 4.8616. Min Act: -0.1700
Data Index: 517207 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9866. Min Range: -4.9866
Max Act: 4.8616. Min Act: -0.1700
Data Index: 6899283 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9866. Min Range: -4.9866
Max Act: 4.8616. Min Act: -0.1700
Data Index: 1149910 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9866. Min Range: -4.9866
Max Act: 4.8616. Min Act: -0.1700
Data Index: 694747 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9866. Min Range: -4.9866
Max Act: 4.8616. Min Act: -0.1700
Data Index: 5517394 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9866. Min Range: -4.9866
Max Act: 4.8616. Min Act: -0.1700
Data Index: 7890009 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9866. Min Range: -4.9866
Max Act: 4.8616. Min Act: -0.1700
Data Index: 1739961 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9866. Min Range: -4.9866
Max Act: 4.7679. Min Act: -0.1700
Data Index: 6264565 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9866. Min Range: -4.9866
Max Act: 4.7991. Min Act: -0.1700
Data Index: 5436522 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9866. Min Range: -4.9866
Max Act: 4.7991. Min Act: -0.1700
Data Index: 7631562 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9866. Min Range: -4.9866
Max Act: 4.7991. Min Act: -0.1700
Data Index: 3382435 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9866. Min Range: -4.9866
Max Act: 4.7679. Min Act: -0.1700
Data Index: 446840 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9866. Min Range: -4.9866
Max Act: 4.7679. Min Act: -0.1700
Data Index: 3892342 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #19