Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3394 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.3368. Min Range: -5.3368
Max Act: 5.3368. Min Act: -0.1700
Data Index: 604495 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3368. Min Range: -5.3368
Max Act: 5.3368. Min Act: -0.1700
Data Index: 3682348 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3368. Min Range: -5.3368
Max Act: 5.1805. Min Act: -0.1700
Data Index: 3484842 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3368. Min Range: -5.3368
Max Act: 5.1180. Min Act: -0.1700
Data Index: 4410945 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3368. Min Range: -5.3368
Max Act: 5.0868. Min Act: -0.1700
Data Index: 1894877 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3368. Min Range: -5.3368
Max Act: 5.0243. Min Act: -0.1700
Data Index: 7635447 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3368. Min Range: -5.3368
Max Act: 5.0243. Min Act: -0.1700
Data Index: 1531509 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3368. Min Range: -5.3368
Max Act: 5.0555. Min Act: -0.1700
Data Index: 1990103 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3368. Min Range: -5.3368
Max Act: 4.9930. Min Act: -0.1700
Data Index: 8794809 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3368. Min Range: -5.3368
Max Act: 4.9930. Min Act: -0.1700
Data Index: 702778 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3368. Min Range: -5.3368
Max Act: 4.9618. Min Act: -0.1700
Data Index: 5180263 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3368. Min Range: -5.3368
Max Act: 4.9930. Min Act: -0.1700
Data Index: 7970668 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3368. Min Range: -5.3368
Max Act: 4.9930. Min Act: -0.1700
Data Index: 1235591 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3368. Min Range: -5.3368
Max Act: 4.9618. Min Act: -0.1700
Data Index: 702777 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3368. Min Range: -5.3368
Max Act: 4.8993. Min Act: -0.1700
Data Index: 4560492 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3368. Min Range: -5.3368
Max Act: 4.8680. Min Act: -0.1700
Data Index: 430755 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3368. Min Range: -5.3368
Max Act: 4.8993. Min Act: -0.1700
Data Index: 1680985 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3368. Min Range: -5.3368
Max Act: 4.8993. Min Act: -0.1700
Data Index: 5113420 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3368. Min Range: -5.3368
Max Act: 4.8993. Min Act: -0.1700
Data Index: 4889868 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3368. Min Range: -5.3368
Max Act: 4.9305. Min Act: -0.1700
Data Index: 3240558 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #19