Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1761 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.9373. Min Range: -6.9373
Max Act: 6.9373. Min Act: -0.1700
Data Index: 1500941 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9373. Min Range: -6.9373
Max Act: 6.8436. Min Act: -0.1700
Data Index: 4130291 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9373. Min Range: -6.9373
Max Act: 6.8436. Min Act: -0.1700
Data Index: 1281513 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9373. Min Range: -6.9373
Max Act: 6.8436. Min Act: -0.1700
Data Index: 7651963 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9373. Min Range: -6.9373
Max Act: 6.8436. Min Act: -0.1700
Data Index: 615683 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9373. Min Range: -6.9373
Max Act: 6.7811. Min Act: -0.1700
Data Index: 2036602 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9373. Min Range: -6.9373
Max Act: 6.7498. Min Act: -0.1700
Data Index: 2323711 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9373. Min Range: -6.9373
Max Act: 6.7498. Min Act: -0.1700
Data Index: 1819656 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9373. Min Range: -6.9373
Max Act: 6.7811. Min Act: -0.1700
Data Index: 1553321 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9373. Min Range: -6.9373
Max Act: 6.7186. Min Act: -0.1700
Data Index: 5036702 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9373. Min Range: -6.9373
Max Act: 6.6873. Min Act: -0.1700
Data Index: 6609363 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9373. Min Range: -6.9373
Max Act: 6.6873. Min Act: -0.1700
Data Index: 351745 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9373. Min Range: -6.9373
Max Act: 6.6873. Min Act: -0.1700
Data Index: 126445 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9373. Min Range: -6.9373
Max Act: 6.6873. Min Act: -0.1700
Data Index: 4818714 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9373. Min Range: -6.9373
Max Act: 6.6873. Min Act: -0.1700
Data Index: 6226326 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9373. Min Range: -6.9373
Max Act: 6.6561. Min Act: -0.1700
Data Index: 5469421 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9373. Min Range: -6.9373
Max Act: 6.6561. Min Act: -0.1700
Data Index: 7675897 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9373. Min Range: -6.9373
Max Act: 6.6248. Min Act: -0.1700
Data Index: 3457098 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9373. Min Range: -6.9373
Max Act: 6.6248. Min Act: -0.1700
Data Index: 8755829 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9373. Min Range: -6.9373
Max Act: 6.6248. Min Act: -0.1700
Data Index: 5264234 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #19