Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3121 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2184. Min Range: -6.2184
Max Act: 6.2184. Min Act: -0.1700
Data Index: 2707378 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2184. Min Range: -6.2184
Max Act: 5.9059. Min Act: -0.1700
Data Index: 2853360 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2184. Min Range: -6.2184
Max Act: 5.8746. Min Act: -0.1700
Data Index: 5249679 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2184. Min Range: -6.2184
Max Act: 5.8434. Min Act: -0.1700
Data Index: 4973146 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2184. Min Range: -6.2184
Max Act: 5.8434. Min Act: -0.1700
Data Index: 4206817 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2184. Min Range: -6.2184
Max Act: 5.8121. Min Act: -0.1700
Data Index: 1080756 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2184. Min Range: -6.2184
Max Act: 5.7809. Min Act: -0.1700
Data Index: 2252615 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2184. Min Range: -6.2184
Max Act: 5.7496. Min Act: -0.1700
Data Index: 7694757 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2184. Min Range: -6.2184
Max Act: 5.7496. Min Act: -0.1700
Data Index: 5638087 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2184. Min Range: -6.2184
Max Act: 5.7496. Min Act: -0.1700
Data Index: 1383882 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2184. Min Range: -6.2184
Max Act: 5.7184. Min Act: -0.1700
Data Index: 171317 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2184. Min Range: -6.2184
Max Act: 5.6871. Min Act: -0.1700
Data Index: 5123611 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2184. Min Range: -6.2184
Max Act: 5.7184. Min Act: -0.1700
Data Index: 6216315 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2184. Min Range: -6.2184
Max Act: 5.6871. Min Act: -0.1700
Data Index: 797782 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2184. Min Range: -6.2184
Max Act: 5.6871. Min Act: -0.1700
Data Index: 6975269 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2184. Min Range: -6.2184
Max Act: 5.6559. Min Act: -0.1700
Data Index: 8577756 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2184. Min Range: -6.2184
Max Act: 5.6559. Min Act: -0.1700
Data Index: 2930729 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2184. Min Range: -6.2184
Max Act: 5.6559. Min Act: -0.1700
Data Index: 2448885 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2184. Min Range: -6.2184
Max Act: 5.6246. Min Act: -0.1700
Data Index: 830923 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2184. Min Range: -6.2184
Max Act: 5.5934. Min Act: -0.1700
Data Index: 4674455 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #19