Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1073 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5177. Min Range: -7.5177
Max Act: 7.5177. Min Act: -0.1700
Data Index: 485359 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5177. Min Range: -7.5177
Max Act: 7.4552. Min Act: -0.1700
Data Index: 8816853 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5177. Min Range: -7.5177
Max Act: 7.4239. Min Act: -0.1700
Data Index: 4503420 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5177. Min Range: -7.5177
Max Act: 7.3927. Min Act: -0.1700
Data Index: 717156 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5177. Min Range: -7.5177
Max Act: 7.3927. Min Act: -0.1700
Data Index: 1612156 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5177. Min Range: -7.5177
Max Act: 7.3614. Min Act: -0.1700
Data Index: 1922422 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5177. Min Range: -7.5177
Max Act: 7.3302. Min Act: -0.1700
Data Index: 5061809 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5177. Min Range: -7.5177
Max Act: 7.3302. Min Act: -0.1700
Data Index: 1612155 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5177. Min Range: -7.5177
Max Act: 7.2364. Min Act: -0.1700
Data Index: 3979981 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5177. Min Range: -7.5177
Max Act: 7.2989. Min Act: -0.1700
Data Index: 6819504 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5177. Min Range: -7.5177
Max Act: 7.2989. Min Act: -0.1700
Data Index: 3700203 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5177. Min Range: -7.5177
Max Act: 7.2364. Min Act: -0.1700
Data Index: 900849 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5177. Min Range: -7.5177
Max Act: 7.2052. Min Act: -0.1700
Data Index: 5614234 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5177. Min Range: -7.5177
Max Act: 7.2052. Min Act: -0.1700
Data Index: 4162186 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5177. Min Range: -7.5177
Max Act: 7.2052. Min Act: -0.1700
Data Index: 6252825 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5177. Min Range: -7.5177
Max Act: 7.1739. Min Act: -0.1700
Data Index: 6831390 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5177. Min Range: -7.5177
Max Act: 7.1739. Min Act: -0.1700
Data Index: 7949680 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5177. Min Range: -7.5177
Max Act: 7.1739. Min Act: -0.1700
Data Index: 2443796 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5177. Min Range: -7.5177
Max Act: 7.1739. Min Act: -0.1700
Data Index: 2806907 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5177. Min Range: -7.5177
Max Act: 7.1739. Min Act: -0.1700
Data Index: 2344922 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #19