Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3343 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2929. Min Range: -8.2929
Max Act: 8.2929. Min Act: -0.1700
Data Index: 2840035 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2929. Min Range: -8.2929
Max Act: 8.1054. Min Act: -0.1700
Data Index: 5703450 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2929. Min Range: -8.2929
Max Act: 7.9804. Min Act: -0.1700
Data Index: 7514029 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2929. Min Range: -8.2929
Max Act: 8.0429. Min Act: -0.1700
Data Index: 3081816 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2929. Min Range: -8.2929
Max Act: 7.9179. Min Act: -0.1700
Data Index: 951490 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2929. Min Range: -8.2929
Max Act: 7.9179. Min Act: -0.1700
Data Index: 5339632 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2929. Min Range: -8.2929
Max Act: 7.7929. Min Act: -0.1700
Data Index: 4857099 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2929. Min Range: -8.2929
Max Act: 7.6679. Min Act: -0.1700
Data Index: 4093478 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2929. Min Range: -8.2929
Max Act: 7.6054. Min Act: -0.1700
Data Index: 3983670 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2929. Min Range: -8.2929
Max Act: 7.5429. Min Act: -0.1700
Data Index: 1061501 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2929. Min Range: -8.2929
Max Act: 7.5117. Min Act: -0.1700
Data Index: 1843282 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2929. Min Range: -8.2929
Max Act: 7.4492. Min Act: -0.1700
Data Index: 5243518 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2929. Min Range: -8.2929
Max Act: 7.4179. Min Act: -0.1700
Data Index: 4632231 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2929. Min Range: -8.2929
Max Act: 7.4179. Min Act: -0.1700
Data Index: 4552580 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2929. Min Range: -8.2929
Max Act: 7.4179. Min Act: -0.1700
Data Index: 5392333 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2929. Min Range: -8.2929
Max Act: 7.4179. Min Act: -0.1700
Data Index: 2449279 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2929. Min Range: -8.2929
Max Act: 7.3554. Min Act: -0.1700
Data Index: 5337314 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2929. Min Range: -8.2929
Max Act: 7.3867. Min Act: -0.1700
Data Index: 8781762 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2929. Min Range: -8.2929
Max Act: 7.3867. Min Act: -0.1700
Data Index: 7363025 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2929. Min Range: -8.2929
Max Act: 7.3554. Min Act: -0.1700
Data Index: 2380701 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #19