Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1385 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.3274. Min Range: -5.3274
Max Act: 5.3274. Min Act: -0.1700
Data Index: 488835 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3274. Min Range: -5.3274
Max Act: 5.1399. Min Act: -0.1700
Data Index: 8661141 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3274. Min Range: -5.3274
Max Act: 5.0774. Min Act: -0.1700
Data Index: 117583 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3274. Min Range: -5.3274
Max Act: 5.0461. Min Act: -0.1700
Data Index: 2527197 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3274. Min Range: -5.3274
Max Act: 4.9836. Min Act: -0.1700
Data Index: 6880058 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3274. Min Range: -5.3274
Max Act: 4.9836. Min Act: -0.1700
Data Index: 4266431 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3274. Min Range: -5.3274
Max Act: 4.9211. Min Act: -0.1700
Data Index: 682444 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3274. Min Range: -5.3274
Max Act: 4.9211. Min Act: -0.1700
Data Index: 5811811 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3274. Min Range: -5.3274
Max Act: 4.8586. Min Act: -0.1700
Data Index: 3747478 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3274. Min Range: -5.3274
Max Act: 4.8899. Min Act: -0.1700
Data Index: 3984911 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3274. Min Range: -5.3274
Max Act: 4.7961. Min Act: -0.1700
Data Index: 7276049 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3274. Min Range: -5.3274
Max Act: 4.7649. Min Act: -0.1700
Data Index: 5818493 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3274. Min Range: -5.3274
Max Act: 4.7336. Min Act: -0.1700
Data Index: 6154536 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3274. Min Range: -5.3274
Max Act: 4.7336. Min Act: -0.1700
Data Index: 8339630 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3274. Min Range: -5.3274
Max Act: 4.7024. Min Act: -0.1700
Data Index: 4476428 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3274. Min Range: -5.3274
Max Act: 4.7649. Min Act: -0.1700
Data Index: 8082277 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3274. Min Range: -5.3274
Max Act: 4.7024. Min Act: -0.1700
Data Index: 847529 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3274. Min Range: -5.3274
Max Act: 4.7649. Min Act: -0.1700
Data Index: 8036846 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3274. Min Range: -5.3274
Max Act: 4.7336. Min Act: -0.1700
Data Index: 5422733 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3274. Min Range: -5.3274
Max Act: 4.6711. Min Act: -0.1700
Data Index: 6661710 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #19