Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2087 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4445. Min Range: -6.4445
Max Act: 6.4445. Min Act: -0.1700
Data Index: 772876 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4445. Min Range: -6.4445
Max Act: 6.0695. Min Act: -0.1700
Data Index: 3851118 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4445. Min Range: -6.4445
Max Act: 5.8508. Min Act: -0.1700
Data Index: 1864544 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4445. Min Range: -6.4445
Max Act: 5.8508. Min Act: -0.1700
Data Index: 1815124 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4445. Min Range: -6.4445
Max Act: 5.8195. Min Act: -0.1700
Data Index: 6327264 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4445. Min Range: -6.4445
Max Act: 5.6945. Min Act: -0.1700
Data Index: 287854 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4445. Min Range: -6.4445
Max Act: 5.7258. Min Act: -0.1700
Data Index: 4901706 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4445. Min Range: -6.4445
Max Act: 5.6945. Min Act: -0.1700
Data Index: 1671659 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4445. Min Range: -6.4445
Max Act: 5.6633. Min Act: -0.1700
Data Index: 4292985 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4445. Min Range: -6.4445
Max Act: 5.6633. Min Act: -0.1700
Data Index: 6638060 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4445. Min Range: -6.4445
Max Act: 5.6320. Min Act: -0.1700
Data Index: 5798638 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4445. Min Range: -6.4445
Max Act: 5.5695. Min Act: -0.1700
Data Index: 3681242 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4445. Min Range: -6.4445
Max Act: 5.6008. Min Act: -0.1700
Data Index: 3374038 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4445. Min Range: -6.4445
Max Act: 5.6008. Min Act: -0.1700
Data Index: 274125 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4445. Min Range: -6.4445
Max Act: 5.5695. Min Act: -0.1700
Data Index: 2009885 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4445. Min Range: -6.4445
Max Act: 5.5695. Min Act: -0.1700
Data Index: 1845888 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4445. Min Range: -6.4445
Max Act: 5.5070. Min Act: -0.1700
Data Index: 7837444 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4445. Min Range: -6.4445
Max Act: 5.5070. Min Act: -0.1700
Data Index: 916825 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4445. Min Range: -6.4445
Max Act: 5.4758. Min Act: -0.1700
Data Index: 3858716 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4445. Min Range: -6.4445
Max Act: 5.4758. Min Act: -0.1700
Data Index: 3019713 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #19