Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4503 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.6810. Min Range: -5.6810
Max Act: 5.6810. Min Act: -0.1700
Data Index: 8731439 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6810. Min Range: -5.6810
Max Act: 5.6185. Min Act: -0.1700
Data Index: 3057030 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6810. Min Range: -5.6810
Max Act: 5.5248. Min Act: -0.1700
Data Index: 1717453 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6810. Min Range: -5.6810
Max Act: 5.4935. Min Act: -0.1700
Data Index: 4387642 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6810. Min Range: -5.6810
Max Act: 5.5248. Min Act: -0.1700
Data Index: 7579059 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6810. Min Range: -5.6810
Max Act: 5.3998. Min Act: -0.1700
Data Index: 3414860 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6810. Min Range: -5.6810
Max Act: 5.4310. Min Act: -0.1700
Data Index: 1695007 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6810. Min Range: -5.6810
Max Act: 5.3685. Min Act: -0.1700
Data Index: 1575415 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6810. Min Range: -5.6810
Max Act: 5.3685. Min Act: -0.1700
Data Index: 8332271 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6810. Min Range: -5.6810
Max Act: 5.3373. Min Act: -0.1700
Data Index: 8057112 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6810. Min Range: -5.6810
Max Act: 5.3373. Min Act: -0.1700
Data Index: 6942732 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6810. Min Range: -5.6810
Max Act: 5.3060. Min Act: -0.1700
Data Index: 8393319 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6810. Min Range: -5.6810
Max Act: 5.3373. Min Act: -0.1700
Data Index: 5618336 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6810. Min Range: -5.6810
Max Act: 5.3060. Min Act: -0.1700
Data Index: 5356298 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6810. Min Range: -5.6810
Max Act: 5.3060. Min Act: -0.1700
Data Index: 5908982 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6810. Min Range: -5.6810
Max Act: 5.2748. Min Act: -0.1700
Data Index: 493036 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6810. Min Range: -5.6810
Max Act: 5.2435. Min Act: -0.1700
Data Index: 3876255 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6810. Min Range: -5.6810
Max Act: 5.2435. Min Act: -0.1700
Data Index: 6814286 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6810. Min Range: -5.6810
Max Act: 5.3060. Min Act: -0.1700
Data Index: 8046107 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6810. Min Range: -5.6810
Max Act: 5.2748. Min Act: -0.1700
Data Index: 2084234 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #19