Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2591 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.3436. Min Range: -4.3436
Max Act: 4.3436. Min Act: -0.1700
Data Index: 870904 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3436. Min Range: -4.3436
Max Act: 4.2498. Min Act: -0.1700
Data Index: 6806837 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3436. Min Range: -4.3436
Max Act: 4.2811. Min Act: -0.1700
Data Index: 5932225 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3436. Min Range: -4.3436
Max Act: 4.2811. Min Act: -0.1700
Data Index: 6577714 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3436. Min Range: -4.3436
Max Act: 4.2185. Min Act: -0.1700
Data Index: 6995109 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3436. Min Range: -4.3436
Max Act: 4.2185. Min Act: -0.1700
Data Index: 3977901 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3436. Min Range: -4.3436
Max Act: 4.2185. Min Act: -0.1700
Data Index: 2536228 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3436. Min Range: -4.3436
Max Act: 4.2185. Min Act: -0.1700
Data Index: 6315604 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3436. Min Range: -4.3436
Max Act: 4.1873. Min Act: -0.1700
Data Index: 1925080 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3436. Min Range: -4.3436
Max Act: 4.2185. Min Act: -0.1700
Data Index: 8159782 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3436. Min Range: -4.3436
Max Act: 4.1560. Min Act: -0.1700
Data Index: 5581101 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3436. Min Range: -4.3436
Max Act: 4.1560. Min Act: -0.1700
Data Index: 1888290 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3436. Min Range: -4.3436
Max Act: 4.1560. Min Act: -0.1700
Data Index: 6820581 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3436. Min Range: -4.3436
Max Act: 4.1248. Min Act: -0.1700
Data Index: 4878666 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3436. Min Range: -4.3436
Max Act: 4.0935. Min Act: -0.1700
Data Index: 2018198 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3436. Min Range: -4.3436
Max Act: 4.1248. Min Act: -0.1700
Data Index: 5987877 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3436. Min Range: -4.3436
Max Act: 4.1248. Min Act: -0.1700
Data Index: 6665449 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3436. Min Range: -4.3436
Max Act: 4.1248. Min Act: -0.1700
Data Index: 5496705 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3436. Min Range: -4.3436
Max Act: 4.1248. Min Act: -0.1700
Data Index: 4049059 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3436. Min Range: -4.3436
Max Act: 4.1248. Min Act: -0.1700
Data Index: 3098236 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #19