Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 213 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8767. Min Range: -4.8767
Max Act: 4.8767. Min Act: -0.1700
Data Index: 5108735 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8767. Min Range: -4.8767
Max Act: 4.8142. Min Act: -0.1700
Data Index: 526583 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8767. Min Range: -4.8767
Max Act: 4.7517. Min Act: -0.1700
Data Index: 4002207 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8767. Min Range: -4.8767
Max Act: 4.6580. Min Act: -0.1700
Data Index: 5296905 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8767. Min Range: -4.8767
Max Act: 4.5330. Min Act: -0.1700
Data Index: 620640 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8767. Min Range: -4.8767
Max Act: 4.5330. Min Act: -0.1700
Data Index: 7947719 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8767. Min Range: -4.8767
Max Act: 4.5330. Min Act: -0.1700
Data Index: 2730518 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8767. Min Range: -4.8767
Max Act: 4.5330. Min Act: -0.1700
Data Index: 2864996 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8767. Min Range: -4.8767
Max Act: 4.5017. Min Act: -0.1700
Data Index: 4822453 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8767. Min Range: -4.8767
Max Act: 4.5017. Min Act: -0.1700
Data Index: 6225125 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8767. Min Range: -4.8767
Max Act: 4.5017. Min Act: -0.1700
Data Index: 1146927 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8767. Min Range: -4.8767
Max Act: 4.5017. Min Act: -0.1700
Data Index: 6118264 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8767. Min Range: -4.8767
Max Act: 4.4705. Min Act: -0.1700
Data Index: 3523537 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8767. Min Range: -4.8767
Max Act: 4.5017. Min Act: -0.1700
Data Index: 5361068 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8767. Min Range: -4.8767
Max Act: 4.5017. Min Act: -0.1700
Data Index: 7334505 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8767. Min Range: -4.8767
Max Act: 4.4705. Min Act: -0.1700
Data Index: 6529460 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8767. Min Range: -4.8767
Max Act: 4.4705. Min Act: -0.1700
Data Index: 6648984 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8767. Min Range: -4.8767
Max Act: 4.4705. Min Act: -0.1700
Data Index: 573824 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8767. Min Range: -4.8767
Max Act: 4.4392. Min Act: -0.1700
Data Index: 3650922 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8767. Min Range: -4.8767
Max Act: 4.4392. Min Act: -0.1700
Data Index: 4095687 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #19