Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3205 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.7345. Min Range: -8.7345
Max Act: 8.7345. Min Act: -0.1700
Data Index: 3825370 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7345. Min Range: -8.7345
Max Act: 8.0470. Min Act: -0.1700
Data Index: 4235405 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7345. Min Range: -8.7345
Max Act: 7.7970. Min Act: -0.1700
Data Index: 5080816 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7345. Min Range: -8.7345
Max Act: 7.7658. Min Act: -0.1700
Data Index: 8548514 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7345. Min Range: -8.7345
Max Act: 7.6720. Min Act: -0.1700
Data Index: 3485482 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7345. Min Range: -8.7345
Max Act: 7.6408. Min Act: -0.1700
Data Index: 3554241 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7345. Min Range: -8.7345
Max Act: 7.6095. Min Act: -0.1700
Data Index: 225645 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7345. Min Range: -8.7345
Max Act: 7.5783. Min Act: -0.1700
Data Index: 5012457 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7345. Min Range: -8.7345
Max Act: 7.5470. Min Act: -0.1700
Data Index: 2658270 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7345. Min Range: -8.7345
Max Act: 7.5470. Min Act: -0.1700
Data Index: 8054221 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7345. Min Range: -8.7345
Max Act: 7.5783. Min Act: -0.1700
Data Index: 5165003 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7345. Min Range: -8.7345
Max Act: 7.5470. Min Act: -0.1700
Data Index: 8495841 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7345. Min Range: -8.7345
Max Act: 7.5470. Min Act: -0.1700
Data Index: 4588251 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7345. Min Range: -8.7345
Max Act: 7.5158. Min Act: -0.1700
Data Index: 2542075 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7345. Min Range: -8.7345
Max Act: 7.5158. Min Act: -0.1700
Data Index: 6833027 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7345. Min Range: -8.7345
Max Act: 7.5158. Min Act: -0.1700
Data Index: 5666481 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7345. Min Range: -8.7345
Max Act: 7.4533. Min Act: -0.1700
Data Index: 2914884 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7345. Min Range: -8.7345
Max Act: 7.4845. Min Act: -0.1700
Data Index: 1652931 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7345. Min Range: -8.7345
Max Act: 7.4845. Min Act: -0.1700
Data Index: 7901374 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7345. Min Range: -8.7345
Max Act: 7.4533. Min Act: -0.1700
Data Index: 1527216 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #19