Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3748 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2711. Min Range: -7.2711
Max Act: 7.2711. Min Act: -0.1700
Data Index: 5965394 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2711. Min Range: -7.2711
Max Act: 7.0523. Min Act: -0.1700
Data Index: 2386013 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2711. Min Range: -7.2711
Max Act: 6.9898. Min Act: -0.1700
Data Index: 5788980 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2711. Min Range: -7.2711
Max Act: 6.9586. Min Act: -0.1700
Data Index: 3870330 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2711. Min Range: -7.2711
Max Act: 6.9898. Min Act: -0.1700
Data Index: 7362271 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2711. Min Range: -7.2711
Max Act: 6.8961. Min Act: -0.1700
Data Index: 1798216 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2711. Min Range: -7.2711
Max Act: 6.8336. Min Act: -0.1700
Data Index: 1724325 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2711. Min Range: -7.2711
Max Act: 6.8336. Min Act: -0.1700
Data Index: 8604003 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2711. Min Range: -7.2711
Max Act: 6.7398. Min Act: -0.1700
Data Index: 2673314 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2711. Min Range: -7.2711
Max Act: 6.7086. Min Act: -0.1700
Data Index: 1043973 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2711. Min Range: -7.2711
Max Act: 6.7086. Min Act: -0.1700
Data Index: 4009094 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2711. Min Range: -7.2711
Max Act: 6.7086. Min Act: -0.1700
Data Index: 1908069 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2711. Min Range: -7.2711
Max Act: 6.6773. Min Act: -0.1700
Data Index: 648035 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2711. Min Range: -7.2711
Max Act: 6.6773. Min Act: -0.1700
Data Index: 297126 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2711. Min Range: -7.2711
Max Act: 6.6461. Min Act: -0.1700
Data Index: 1727469 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2711. Min Range: -7.2711
Max Act: 6.6773. Min Act: -0.1700
Data Index: 7986800 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2711. Min Range: -7.2711
Max Act: 6.6461. Min Act: -0.1700
Data Index: 4921458 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2711. Min Range: -7.2711
Max Act: 6.6148. Min Act: -0.1700
Data Index: 7999351 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2711. Min Range: -7.2711
Max Act: 6.6461. Min Act: -0.1700
Data Index: 2579807 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2711. Min Range: -7.2711
Max Act: 6.6148. Min Act: -0.1700
Data Index: 4221269 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #19