Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1335 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8008. Min Range: -5.8008
Max Act: 5.8008. Min Act: -0.1700
Data Index: 4904741 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8008. Min Range: -5.8008
Max Act: 5.2696. Min Act: -0.1700
Data Index: 1210947 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8008. Min Range: -5.8008
Max Act: 5.2071. Min Act: -0.1700
Data Index: 7877600 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8008. Min Range: -5.8008
Max Act: 5.1446. Min Act: -0.1700
Data Index: 4160349 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8008. Min Range: -5.8008
Max Act: 5.1133. Min Act: -0.1700
Data Index: 6348486 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8008. Min Range: -5.8008
Max Act: 5.0821. Min Act: -0.1700
Data Index: 2149415 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8008. Min Range: -5.8008
Max Act: 5.0821. Min Act: -0.1700
Data Index: 6330892 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8008. Min Range: -5.8008
Max Act: 5.0196. Min Act: -0.1700
Data Index: 126540 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8008. Min Range: -5.8008
Max Act: 5.0196. Min Act: -0.1700
Data Index: 1312590 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8008. Min Range: -5.8008
Max Act: 4.9571. Min Act: -0.1700
Data Index: 4383355 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8008. Min Range: -5.8008
Max Act: 4.9883. Min Act: -0.1700
Data Index: 2786244 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8008. Min Range: -5.8008
Max Act: 4.9883. Min Act: -0.1700
Data Index: 5329031 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8008. Min Range: -5.8008
Max Act: 4.9571. Min Act: -0.1700
Data Index: 7745258 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8008. Min Range: -5.8008
Max Act: 4.9258. Min Act: -0.1700
Data Index: 6079782 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8008. Min Range: -5.8008
Max Act: 4.9258. Min Act: -0.1700
Data Index: 3319266 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8008. Min Range: -5.8008
Max Act: 4.9571. Min Act: -0.1700
Data Index: 4501002 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8008. Min Range: -5.8008
Max Act: 4.9258. Min Act: -0.1700
Data Index: 383628 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8008. Min Range: -5.8008
Max Act: 4.8946. Min Act: -0.1700
Data Index: 7311593 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8008. Min Range: -5.8008
Max Act: 4.9258. Min Act: -0.1700
Data Index: 180014 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8008. Min Range: -5.8008
Max Act: 4.8946. Min Act: -0.1700
Data Index: 7282684 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #19