Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1267 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.2428. Min Range: -1.2428
Max Act: 1.2428. Min Act: -0.1698
Data Index: 2461430 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.2428. Min Range: -1.2428
Max Act: 1.2076. Min Act: -0.1700
Data Index: 8516352 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.2428. Min Range: -1.2428
Max Act: 1.2252. Min Act: -0.1700
Data Index: 6069025 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.2428. Min Range: -1.2428
Max Act: 1.1724. Min Act: -0.1700
Data Index: 6696296 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.2428. Min Range: -1.2428
Max Act: 1.1548. Min Act: -0.1700
Data Index: 1732852 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.2428. Min Range: -1.2428
Max Act: 1.1724. Min Act: -0.1700
Data Index: 7435986 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.2428. Min Range: -1.2428
Max Act: 1.1548. Min Act: -0.1699
Data Index: 4113036 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.2428. Min Range: -1.2428
Max Act: 1.1724. Min Act: -0.1700
Data Index: 8706288 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.2428. Min Range: -1.2428
Max Act: 1.1548. Min Act: -0.1700
Data Index: 6252332 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.2428. Min Range: -1.2428
Max Act: 1.1548. Min Act: -0.1700
Data Index: 594777 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.2428. Min Range: -1.2428
Max Act: 1.1372. Min Act: -0.1700
Data Index: 3486350 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.2428. Min Range: -1.2428
Max Act: 1.1372. Min Act: -0.1700
Data Index: 1403368 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.2428. Min Range: -1.2428
Max Act: 1.1197. Min Act: -0.1700
Data Index: 3442715 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.2428. Min Range: -1.2428
Max Act: 1.1197. Min Act: -0.1700
Data Index: 8630074 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.2428. Min Range: -1.2428
Max Act: 1.1197. Min Act: -0.1700
Data Index: 623053 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.2428. Min Range: -1.2428
Max Act: 1.1021. Min Act: -0.1700
Data Index: 13489 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.2428. Min Range: -1.2428
Max Act: 1.0934. Min Act: -0.1700
Data Index: 2776193 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.2428. Min Range: -1.2428
Max Act: 1.0934. Min Act: -0.1700
Data Index: 4426819 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.2428. Min Range: -1.2428
Max Act: 1.0759. Min Act: -0.1700
Data Index: 13734 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.2428. Min Range: -1.2428
Max Act: 1.0846. Min Act: -0.1700
Data Index: 7453016 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #19