Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 829 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5546. Min Range: -6.5546
Max Act: 6.5546. Min Act: -0.1700
Data Index: 3154250 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5546. Min Range: -6.5546
Max Act: 6.4608. Min Act: -0.1700
Data Index: 6002389 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5546. Min Range: -6.5546
Max Act: 6.4296. Min Act: -0.1700
Data Index: 4964676 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5546. Min Range: -6.5546
Max Act: 6.4296. Min Act: -0.1700
Data Index: 4248494 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5546. Min Range: -6.5546
Max Act: 6.2733. Min Act: -0.1700
Data Index: 1820957 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5546. Min Range: -6.5546
Max Act: 6.3046. Min Act: -0.1700
Data Index: 6794206 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5546. Min Range: -6.5546
Max Act: 6.2733. Min Act: -0.1700
Data Index: 1626485 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5546. Min Range: -6.5546
Max Act: 6.3046. Min Act: -0.1700
Data Index: 7688637 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5546. Min Range: -6.5546
Max Act: 6.1796. Min Act: -0.1700
Data Index: 1973276 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5546. Min Range: -6.5546
Max Act: 6.1483. Min Act: -0.1700
Data Index: 237581 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5546. Min Range: -6.5546
Max Act: 6.1483. Min Act: -0.1700
Data Index: 2972500 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5546. Min Range: -6.5546
Max Act: 6.1171. Min Act: -0.1700
Data Index: 5571090 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5546. Min Range: -6.5546
Max Act: 6.0858. Min Act: -0.1700
Data Index: 103800 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5546. Min Range: -6.5546
Max Act: 6.0546. Min Act: -0.1700
Data Index: 2541492 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5546. Min Range: -6.5546
Max Act: 6.0546. Min Act: -0.1700
Data Index: 1798581 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5546. Min Range: -6.5546
Max Act: 6.0233. Min Act: -0.1700
Data Index: 2654634 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5546. Min Range: -6.5546
Max Act: 6.0546. Min Act: -0.1700
Data Index: 8362822 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5546. Min Range: -6.5546
Max Act: 6.0233. Min Act: -0.1700
Data Index: 3582726 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5546. Min Range: -6.5546
Max Act: 6.0233. Min Act: -0.1700
Data Index: 6962860 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5546. Min Range: -6.5546
Max Act: 6.0233. Min Act: -0.1700
Data Index: 2087568 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19