Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5523 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3362. Min Range: -8.3362
Max Act: 8.3362. Min Act: -0.1700
Data Index: 8702883 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3362. Min Range: -8.3362
Max Act: 8.2112. Min Act: -0.1700
Data Index: 8702887 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3362. Min Range: -8.3362
Max Act: 7.9612. Min Act: -0.1700
Data Index: 2850544 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3362. Min Range: -8.3362
Max Act: 7.9612. Min Act: -0.1700
Data Index: 1049389 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3362. Min Range: -8.3362
Max Act: 7.8987. Min Act: -0.1700
Data Index: 4651530 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3362. Min Range: -8.3362
Max Act: 7.8987. Min Act: -0.1700
Data Index: 4209191 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3362. Min Range: -8.3362
Max Act: 7.8362. Min Act: -0.1700
Data Index: 7616109 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3362. Min Range: -8.3362
Max Act: 7.7424. Min Act: -0.1700
Data Index: 5419759 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3362. Min Range: -8.3362
Max Act: 7.7112. Min Act: -0.1700
Data Index: 5937431 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3362. Min Range: -8.3362
Max Act: 7.6487. Min Act: -0.1700
Data Index: 1054829 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3362. Min Range: -8.3362
Max Act: 7.6487. Min Act: -0.1700
Data Index: 2085303 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3362. Min Range: -8.3362
Max Act: 7.6174. Min Act: -0.1700
Data Index: 8471429 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3362. Min Range: -8.3362
Max Act: 7.6174. Min Act: -0.1700
Data Index: 8014566 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3362. Min Range: -8.3362
Max Act: 7.6487. Min Act: -0.1700
Data Index: 2795670 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3362. Min Range: -8.3362
Max Act: 7.5862. Min Act: -0.1700
Data Index: 6013151 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3362. Min Range: -8.3362
Max Act: 7.5862. Min Act: -0.1700
Data Index: 5260186 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3362. Min Range: -8.3362
Max Act: 7.5237. Min Act: -0.1700
Data Index: 2503131 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3362. Min Range: -8.3362
Max Act: 7.4924. Min Act: -0.1700
Data Index: 2085276 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3362. Min Range: -8.3362
Max Act: 7.4612. Min Act: -0.1700
Data Index: 8742852 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3362. Min Range: -8.3362
Max Act: 7.4612. Min Act: -0.1700
Data Index: 636527 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #19