Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2050 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6110. Min Range: -6.6110
Max Act: 6.6110. Min Act: -0.1700
Data Index: 347742 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6110. Min Range: -6.6110
Max Act: 6.6110. Min Act: -0.1700
Data Index: 7365082 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6110. Min Range: -6.6110
Max Act: 6.5172. Min Act: -0.1700
Data Index: 6160596 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6110. Min Range: -6.6110
Max Act: 6.4547. Min Act: -0.1700
Data Index: 7232195 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6110. Min Range: -6.6110
Max Act: 6.4547. Min Act: -0.1700
Data Index: 5196825 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6110. Min Range: -6.6110
Max Act: 6.4547. Min Act: -0.1700
Data Index: 636213 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6110. Min Range: -6.6110
Max Act: 6.4235. Min Act: -0.1700
Data Index: 2783884 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6110. Min Range: -6.6110
Max Act: 6.4235. Min Act: -0.1700
Data Index: 5668182 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6110. Min Range: -6.6110
Max Act: 6.3922. Min Act: -0.1700
Data Index: 8317773 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6110. Min Range: -6.6110
Max Act: 6.3922. Min Act: -0.1700
Data Index: 8336355 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6110. Min Range: -6.6110
Max Act: 6.3610. Min Act: -0.1700
Data Index: 6992169 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6110. Min Range: -6.6110
Max Act: 6.3610. Min Act: -0.1700
Data Index: 7447238 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6110. Min Range: -6.6110
Max Act: 6.3610. Min Act: -0.1700
Data Index: 996132 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6110. Min Range: -6.6110
Max Act: 6.3610. Min Act: -0.1700
Data Index: 4186931 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6110. Min Range: -6.6110
Max Act: 6.2985. Min Act: -0.1700
Data Index: 1583440 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6110. Min Range: -6.6110
Max Act: 6.2985. Min Act: -0.1700
Data Index: 5379502 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6110. Min Range: -6.6110
Max Act: 6.2985. Min Act: -0.1700
Data Index: 604238 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6110. Min Range: -6.6110
Max Act: 6.2360. Min Act: -0.1700
Data Index: 3721781 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6110. Min Range: -6.6110
Max Act: 6.2672. Min Act: -0.1700
Data Index: 5933624 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6110. Min Range: -6.6110
Max Act: 6.2047. Min Act: -0.1700
Data Index: 6161281 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #19