Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1743 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8506. Min Range: -6.8506
Max Act: 6.8506. Min Act: -0.1700
Data Index: 8139963 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8506. Min Range: -6.8506
Max Act: 6.6631. Min Act: -0.1700
Data Index: 7003365 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8506. Min Range: -6.8506
Max Act: 6.3506. Min Act: -0.1700
Data Index: 7035709 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8506. Min Range: -6.8506
Max Act: 6.3506. Min Act: -0.1700
Data Index: 3306177 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8506. Min Range: -6.8506
Max Act: 6.2881. Min Act: -0.1700
Data Index: 1114991 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8506. Min Range: -6.8506
Max Act: 6.2256. Min Act: -0.1700
Data Index: 2965081 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8506. Min Range: -6.8506
Max Act: 6.1006. Min Act: -0.1700
Data Index: 5488996 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8506. Min Range: -6.8506
Max Act: 6.1318. Min Act: -0.1700
Data Index: 4500302 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8506. Min Range: -6.8506
Max Act: 6.1318. Min Act: -0.1700
Data Index: 2992925 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8506. Min Range: -6.8506
Max Act: 6.1318. Min Act: -0.1700
Data Index: 2382110 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8506. Min Range: -6.8506
Max Act: 6.1318. Min Act: -0.1700
Data Index: 1439136 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8506. Min Range: -6.8506
Max Act: 6.0693. Min Act: -0.1700
Data Index: 843165 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8506. Min Range: -6.8506
Max Act: 6.1006. Min Act: -0.1700
Data Index: 581643 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8506. Min Range: -6.8506
Max Act: 6.1006. Min Act: -0.1700
Data Index: 2101149 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8506. Min Range: -6.8506
Max Act: 6.1318. Min Act: -0.1700
Data Index: 4088400 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8506. Min Range: -6.8506
Max Act: 6.1006. Min Act: -0.1700
Data Index: 286822 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8506. Min Range: -6.8506
Max Act: 6.0693. Min Act: -0.1700
Data Index: 8152530 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8506. Min Range: -6.8506
Max Act: 6.0693. Min Act: -0.1700
Data Index: 2873527 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8506. Min Range: -6.8506
Max Act: 6.0381. Min Act: -0.1700
Data Index: 8149196 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8506. Min Range: -6.8506
Max Act: 6.0381. Min Act: -0.1700
Data Index: 7563735 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #19