Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2623 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.5891. Min Range: -1.5891
Max Act: 1.5891. Min Act: -0.1700
Data Index: 1033250 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.5891. Min Range: -1.5891
Max Act: 1.5716. Min Act: -0.1691
Data Index: 6817178 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.5891. Min Range: -1.5891
Max Act: 1.5191. Min Act: -0.1699
Data Index: 3342701 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.5891. Min Range: -1.5891
Max Act: 1.4840. Min Act: -0.1700
Data Index: 4137814 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.5891. Min Range: -1.5891
Max Act: 1.4840. Min Act: -0.1700
Data Index: 5316294 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.5891. Min Range: -1.5891
Max Act: 1.4840. Min Act: -0.1700
Data Index: 4097169 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.5891. Min Range: -1.5891
Max Act: 1.4664. Min Act: -0.1700
Data Index: 7362167 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.5891. Min Range: -1.5891
Max Act: 1.4488. Min Act: -0.1700
Data Index: 3941134 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.5891. Min Range: -1.5891
Max Act: 1.4312. Min Act: -0.1700
Data Index: 3452582 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.5891. Min Range: -1.5891
Max Act: 1.4312. Min Act: -0.1700
Data Index: 1046236 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.5891. Min Range: -1.5891
Max Act: 1.4136. Min Act: -0.1700
Data Index: 4139946 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.5891. Min Range: -1.5891
Max Act: 1.4136. Min Act: -0.1700
Data Index: 6016024 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.5891. Min Range: -1.5891
Max Act: 1.3783. Min Act: -0.1699
Data Index: 1702798 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.5891. Min Range: -1.5891
Max Act: 1.3960. Min Act: -0.1700
Data Index: 2610534 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.5891. Min Range: -1.5891
Max Act: 1.3960. Min Act: -0.1698
Data Index: 1985310 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.5891. Min Range: -1.5891
Max Act: 1.3960. Min Act: -0.1700
Data Index: 2795247 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.5891. Min Range: -1.5891
Max Act: 1.3783. Min Act: -0.1700
Data Index: 4576879 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.5891. Min Range: -1.5891
Max Act: 1.3783. Min Act: -0.1700
Data Index: 5508586 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.5891. Min Range: -1.5891
Max Act: 1.3783. Min Act: -0.1700
Data Index: 3426515 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.5891. Min Range: -1.5891
Max Act: 1.3783. Min Act: -0.1700
Data Index: 5308487 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #19