Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3958 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3395. Min Range: -5.3395
Max Act: 5.3083. Min Act: -0.1700
Data Index: 5850564 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3395. Min Range: -5.3395
Max Act: 5.3395. Min Act: -0.1700
Data Index: 6094770 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3395. Min Range: -5.3395
Max Act: 5.2458. Min Act: -0.1700
Data Index: 6833598 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3395. Min Range: -5.3395
Max Act: 5.1520. Min Act: -0.1700
Data Index: 462234 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3395. Min Range: -5.3395
Max Act: 5.1833. Min Act: -0.1700
Data Index: 1028679 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3395. Min Range: -5.3395
Max Act: 5.1208. Min Act: -0.1700
Data Index: 1906322 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3395. Min Range: -5.3395
Max Act: 5.1833. Min Act: -0.1700
Data Index: 2446480 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3395. Min Range: -5.3395
Max Act: 5.1208. Min Act: -0.1700
Data Index: 2475347 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3395. Min Range: -5.3395
Max Act: 5.1208. Min Act: -0.1700
Data Index: 4074658 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3395. Min Range: -5.3395
Max Act: 5.1208. Min Act: -0.1700
Data Index: 5473064 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3395. Min Range: -5.3395
Max Act: 5.0895. Min Act: -0.1700
Data Index: 26918 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3395. Min Range: -5.3395
Max Act: 5.0583. Min Act: -0.1700
Data Index: 5842184 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3395. Min Range: -5.3395
Max Act: 5.0583. Min Act: -0.1700
Data Index: 2410736 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3395. Min Range: -5.3395
Max Act: 5.0895. Min Act: -0.1700
Data Index: 8737494 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3395. Min Range: -5.3395
Max Act: 5.0270. Min Act: -0.1700
Data Index: 209558 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3395. Min Range: -5.3395
Max Act: 5.0270. Min Act: -0.1700
Data Index: 3513195 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3395. Min Range: -5.3395
Max Act: 5.0583. Min Act: -0.1700
Data Index: 7794161 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3395. Min Range: -5.3395
Max Act: 5.0270. Min Act: -0.1700
Data Index: 6909612 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3395. Min Range: -5.3395
Max Act: 4.9958. Min Act: -0.1700
Data Index: 4535502 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3395. Min Range: -5.3395
Max Act: 4.9958. Min Act: -0.1700
Data Index: 1897386 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #19