Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4950 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.2366. Min Range: -6.2366
Max Act: 6.2366. Min Act: -0.1700
Data Index: 8079810 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2366. Min Range: -6.2366
Max Act: 6.1116. Min Act: -0.1700
Data Index: 4174832 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2366. Min Range: -6.2366
Max Act: 6.0804. Min Act: -0.1700
Data Index: 2803268 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2366. Min Range: -6.2366
Max Act: 6.0491. Min Act: -0.1700
Data Index: 379000 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2366. Min Range: -6.2366
Max Act: 6.0179. Min Act: -0.1700
Data Index: 1608646 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2366. Min Range: -6.2366
Max Act: 5.8929. Min Act: -0.1700
Data Index: 6970763 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2366. Min Range: -6.2366
Max Act: 5.8616. Min Act: -0.1700
Data Index: 577370 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2366. Min Range: -6.2366
Max Act: 5.8616. Min Act: -0.1700
Data Index: 5384266 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2366. Min Range: -6.2366
Max Act: 5.8616. Min Act: -0.1700
Data Index: 2874326 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2366. Min Range: -6.2366
Max Act: 5.8616. Min Act: -0.1700
Data Index: 2080447 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2366. Min Range: -6.2366
Max Act: 5.8616. Min Act: -0.1700
Data Index: 2096649 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2366. Min Range: -6.2366
Max Act: 5.8616. Min Act: -0.1700
Data Index: 765703 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2366. Min Range: -6.2366
Max Act: 5.8304. Min Act: -0.1700
Data Index: 6034342 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2366. Min Range: -6.2366
Max Act: 5.8616. Min Act: -0.1700
Data Index: 3147122 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2366. Min Range: -6.2366
Max Act: 5.7991. Min Act: -0.1700
Data Index: 4826430 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2366. Min Range: -6.2366
Max Act: 5.7991. Min Act: -0.1700
Data Index: 482298 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2366. Min Range: -6.2366
Max Act: 5.7991. Min Act: -0.1700
Data Index: 6169856 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2366. Min Range: -6.2366
Max Act: 5.7991. Min Act: -0.1700
Data Index: 3507949 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2366. Min Range: -6.2366
Max Act: 5.7991. Min Act: -0.1700
Data Index: 6669007 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2366. Min Range: -6.2366
Max Act: 5.7679. Min Act: -0.1700
Data Index: 5098861 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #19