Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3217 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4721. Min Range: -5.4721
Max Act: 5.4721. Min Act: -0.1700
Data Index: 612646 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4721. Min Range: -5.4721
Max Act: 5.4721. Min Act: -0.1700
Data Index: 1288900 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4721. Min Range: -5.4721
Max Act: 5.4409. Min Act: -0.1700
Data Index: 4730415 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4721. Min Range: -5.4721
Max Act: 5.4409. Min Act: -0.1700
Data Index: 6679217 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4721. Min Range: -5.4721
Max Act: 5.4096. Min Act: -0.1700
Data Index: 3678179 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4721. Min Range: -5.4721
Max Act: 5.4096. Min Act: -0.1700
Data Index: 953429 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4721. Min Range: -5.4721
Max Act: 5.3784. Min Act: -0.1700
Data Index: 5597290 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4721. Min Range: -5.4721
Max Act: 5.3159. Min Act: -0.1700
Data Index: 165476 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4721. Min Range: -5.4721
Max Act: 5.3159. Min Act: -0.1700
Data Index: 1706721 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4721. Min Range: -5.4721
Max Act: 5.2846. Min Act: -0.1700
Data Index: 8771006 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4721. Min Range: -5.4721
Max Act: 5.2846. Min Act: -0.1700
Data Index: 3303402 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4721. Min Range: -5.4721
Max Act: 5.2534. Min Act: -0.1700
Data Index: 8816720 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4721. Min Range: -5.4721
Max Act: 5.2846. Min Act: -0.1700
Data Index: 1766552 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4721. Min Range: -5.4721
Max Act: 5.2534. Min Act: -0.1700
Data Index: 3774281 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4721. Min Range: -5.4721
Max Act: 5.2221. Min Act: -0.1700
Data Index: 6735505 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4721. Min Range: -5.4721
Max Act: 5.2221. Min Act: -0.1700
Data Index: 1766556 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4721. Min Range: -5.4721
Max Act: 5.1909. Min Act: -0.1700
Data Index: 1308729 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4721. Min Range: -5.4721
Max Act: 5.1909. Min Act: -0.1700
Data Index: 823066 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4721. Min Range: -5.4721
Max Act: 5.1596. Min Act: -0.1700
Data Index: 5270406 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4721. Min Range: -5.4721
Max Act: 5.1596. Min Act: -0.1700
Data Index: 4037408 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #19