Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3056 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4853. Min Range: -6.4853
Max Act: 6.4853. Min Act: -0.1700
Data Index: 6369399 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4853. Min Range: -6.4853
Max Act: 6.4541. Min Act: -0.1700
Data Index: 5709860 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4853. Min Range: -6.4853
Max Act: 6.2353. Min Act: -0.1700
Data Index: 3564813 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4853. Min Range: -6.4853
Max Act: 6.2353. Min Act: -0.1700
Data Index: 7507571 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4853. Min Range: -6.4853
Max Act: 6.1416. Min Act: -0.1700
Data Index: 7885019 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4853. Min Range: -6.4853
Max Act: 6.1103. Min Act: -0.1700
Data Index: 2630947 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4853. Min Range: -6.4853
Max Act: 6.1103. Min Act: -0.1700
Data Index: 5180862 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4853. Min Range: -6.4853
Max Act: 6.0791. Min Act: -0.1700
Data Index: 944773 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4853. Min Range: -6.4853
Max Act: 6.0791. Min Act: -0.1700
Data Index: 7118645 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4853. Min Range: -6.4853
Max Act: 6.1103. Min Act: -0.1700
Data Index: 157182 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4853. Min Range: -6.4853
Max Act: 6.0478. Min Act: -0.1700
Data Index: 5088405 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4853. Min Range: -6.4853
Max Act: 6.0791. Min Act: -0.1700
Data Index: 3032432 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4853. Min Range: -6.4853
Max Act: 6.0166. Min Act: -0.1700
Data Index: 4672052 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4853. Min Range: -6.4853
Max Act: 6.0166. Min Act: -0.1700
Data Index: 8185900 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4853. Min Range: -6.4853
Max Act: 6.0166. Min Act: -0.1700
Data Index: 1554351 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4853. Min Range: -6.4853
Max Act: 5.9853. Min Act: -0.1700
Data Index: 6506910 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4853. Min Range: -6.4853
Max Act: 5.9541. Min Act: -0.1700
Data Index: 3292292 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4853. Min Range: -6.4853
Max Act: 5.9541. Min Act: -0.1700
Data Index: 5166686 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4853. Min Range: -6.4853
Max Act: 5.9541. Min Act: -0.1700
Data Index: 3721152 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4853. Min Range: -6.4853
Max Act: 5.9541. Min Act: -0.1700
Data Index: 2305491 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #19