Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5015 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7676. Min Range: -7.7676
Max Act: 7.7676. Min Act: -0.1700
Data Index: 5427415 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7676. Min Range: -7.7676
Max Act: 7.4551. Min Act: -0.1700
Data Index: 360234 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7676. Min Range: -7.7676
Max Act: 7.4239. Min Act: -0.1700
Data Index: 7507665 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7676. Min Range: -7.7676
Max Act: 7.4551. Min Act: -0.1700
Data Index: 7950457 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7676. Min Range: -7.7676
Max Act: 7.4239. Min Act: -0.1700
Data Index: 1920205 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7676. Min Range: -7.7676
Max Act: 7.3301. Min Act: -0.1700
Data Index: 2192070 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7676. Min Range: -7.7676
Max Act: 7.3614. Min Act: -0.1700
Data Index: 6423155 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7676. Min Range: -7.7676
Max Act: 7.3614. Min Act: -0.1700
Data Index: 6226427 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7676. Min Range: -7.7676
Max Act: 7.3614. Min Act: -0.1700
Data Index: 3890637 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7676. Min Range: -7.7676
Max Act: 7.2989. Min Act: -0.1700
Data Index: 6237296 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7676. Min Range: -7.7676
Max Act: 7.2989. Min Act: -0.1700
Data Index: 3494097 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7676. Min Range: -7.7676
Max Act: 7.2676. Min Act: -0.1700
Data Index: 3646346 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7676. Min Range: -7.7676
Max Act: 7.2364. Min Act: -0.1700
Data Index: 6567807 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7676. Min Range: -7.7676
Max Act: 7.2051. Min Act: -0.1700
Data Index: 2902279 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7676. Min Range: -7.7676
Max Act: 7.2051. Min Act: -0.1700
Data Index: 3217049 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7676. Min Range: -7.7676
Max Act: 7.2051. Min Act: -0.1700
Data Index: 5689935 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7676. Min Range: -7.7676
Max Act: 7.2051. Min Act: -0.1700
Data Index: 5282756 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7676. Min Range: -7.7676
Max Act: 7.1739. Min Act: -0.1700
Data Index: 1567208 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7676. Min Range: -7.7676
Max Act: 7.2051. Min Act: -0.1700
Data Index: 3140926 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7676. Min Range: -7.7676
Max Act: 7.1739. Min Act: -0.1700
Data Index: 5075300 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #19