Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3107 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2586. Min Range: -5.2586
Max Act: 5.2586. Min Act: -0.1700
Data Index: 6664403 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2586. Min Range: -5.2586
Max Act: 5.2586. Min Act: -0.1700
Data Index: 1626867 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2586. Min Range: -5.2586
Max Act: 5.2274. Min Act: -0.1700
Data Index: 865959 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2586. Min Range: -5.2586
Max Act: 5.1961. Min Act: -0.1700
Data Index: 6710457 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2586. Min Range: -5.2586
Max Act: 5.1649. Min Act: -0.1700
Data Index: 4429253 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2586. Min Range: -5.2586
Max Act: 5.1649. Min Act: -0.1700
Data Index: 7130710 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2586. Min Range: -5.2586
Max Act: 5.1336. Min Act: -0.1700
Data Index: 8093817 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2586. Min Range: -5.2586
Max Act: 5.1649. Min Act: -0.1700
Data Index: 2505812 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2586. Min Range: -5.2586
Max Act: 5.1649. Min Act: -0.1700
Data Index: 2563215 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2586. Min Range: -5.2586
Max Act: 5.1649. Min Act: -0.1700
Data Index: 1785151 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2586. Min Range: -5.2586
Max Act: 5.1649. Min Act: -0.1700
Data Index: 8642285 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2586. Min Range: -5.2586
Max Act: 5.1336. Min Act: -0.1700
Data Index: 3906715 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2586. Min Range: -5.2586
Max Act: 5.1649. Min Act: -0.1700
Data Index: 6244493 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2586. Min Range: -5.2586
Max Act: 5.1336. Min Act: -0.1700
Data Index: 6283724 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2586. Min Range: -5.2586
Max Act: 5.1649. Min Act: -0.1700
Data Index: 6293936 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2586. Min Range: -5.2586
Max Act: 5.1336. Min Act: -0.1700
Data Index: 3881742 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2586. Min Range: -5.2586
Max Act: 5.1336. Min Act: -0.1700
Data Index: 5933839 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2586. Min Range: -5.2586
Max Act: 5.1336. Min Act: -0.1700
Data Index: 3335117 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2586. Min Range: -5.2586
Max Act: 5.1336. Min Act: -0.1700
Data Index: 2627103 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2586. Min Range: -5.2586
Max Act: 5.1336. Min Act: -0.1700
Data Index: 5395174 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #19