Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4968 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4463. Min Range: -4.4463
Max Act: 4.4463. Min Act: -0.1700
Data Index: 8647406 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4463. Min Range: -4.4463
Max Act: 4.3213. Min Act: -0.1700
Data Index: 7291202 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4463. Min Range: -4.4463
Max Act: 4.2900. Min Act: -0.1700
Data Index: 6582558 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4463. Min Range: -4.4463
Max Act: 4.2588. Min Act: -0.1700
Data Index: 4114220 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4463. Min Range: -4.4463
Max Act: 4.2275. Min Act: -0.1700
Data Index: 7291203 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4463. Min Range: -4.4463
Max Act: 4.1963. Min Act: -0.1700
Data Index: 2046295 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4463. Min Range: -4.4463
Max Act: 4.1650. Min Act: -0.1700
Data Index: 6458387 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4463. Min Range: -4.4463
Max Act: 4.1338. Min Act: -0.1700
Data Index: 1996043 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4463. Min Range: -4.4463
Max Act: 4.1025. Min Act: -0.1700
Data Index: 5484953 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4463. Min Range: -4.4463
Max Act: 4.1025. Min Act: -0.1700
Data Index: 6304268 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4463. Min Range: -4.4463
Max Act: 4.1025. Min Act: -0.1700
Data Index: 6433104 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4463. Min Range: -4.4463
Max Act: 4.1025. Min Act: -0.1700
Data Index: 2241004 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4463. Min Range: -4.4463
Max Act: 4.0400. Min Act: -0.1700
Data Index: 7899186 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4463. Min Range: -4.4463
Max Act: 4.0713. Min Act: -0.1700
Data Index: 246198 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4463. Min Range: -4.4463
Max Act: 4.0713. Min Act: -0.1700
Data Index: 2863929 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4463. Min Range: -4.4463
Max Act: 4.0713. Min Act: -0.1700
Data Index: 3916246 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4463. Min Range: -4.4463
Max Act: 4.0713. Min Act: -0.1700
Data Index: 3775374 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4463. Min Range: -4.4463
Max Act: 4.0400. Min Act: -0.1700
Data Index: 7467070 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4463. Min Range: -4.4463
Max Act: 4.0400. Min Act: -0.1700
Data Index: 400978 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4463. Min Range: -4.4463
Max Act: 4.0400. Min Act: -0.1700
Data Index: 2596425 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #19