Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3081 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8451. Min Range: -7.8451
Max Act: 7.8451. Min Act: -0.1700
Data Index: 935553 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8451. Min Range: -7.8451
Max Act: 7.7514. Min Act: -0.1700
Data Index: 5985299 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8451. Min Range: -7.8451
Max Act: 7.7514. Min Act: -0.1700
Data Index: 4809637 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8451. Min Range: -7.8451
Max Act: 7.7201. Min Act: -0.1700
Data Index: 2796023 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8451. Min Range: -7.8451
Max Act: 7.6576. Min Act: -0.1700
Data Index: 3361014 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8451. Min Range: -7.8451
Max Act: 7.6576. Min Act: -0.1700
Data Index: 8601633 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8451. Min Range: -7.8451
Max Act: 7.5951. Min Act: -0.1700
Data Index: 6767307 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8451. Min Range: -7.8451
Max Act: 7.5639. Min Act: -0.1700
Data Index: 4909816 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8451. Min Range: -7.8451
Max Act: 7.4701. Min Act: -0.1700
Data Index: 5540843 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8451. Min Range: -7.8451
Max Act: 7.5014. Min Act: -0.1700
Data Index: 4491259 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8451. Min Range: -7.8451
Max Act: 7.4701. Min Act: -0.1700
Data Index: 639957 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8451. Min Range: -7.8451
Max Act: 7.4701. Min Act: -0.1700
Data Index: 1683314 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8451. Min Range: -7.8451
Max Act: 7.4389. Min Act: -0.1700
Data Index: 5917736 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8451. Min Range: -7.8451
Max Act: 7.4389. Min Act: -0.1700
Data Index: 5352180 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8451. Min Range: -7.8451
Max Act: 7.4389. Min Act: -0.1700
Data Index: 4992086 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8451. Min Range: -7.8451
Max Act: 7.4389. Min Act: -0.1700
Data Index: 2256835 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8451. Min Range: -7.8451
Max Act: 7.4076. Min Act: -0.1700
Data Index: 5773618 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8451. Min Range: -7.8451
Max Act: 7.3764. Min Act: -0.1700
Data Index: 5339236 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8451. Min Range: -7.8451
Max Act: 7.3451. Min Act: -0.1700
Data Index: 464450 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8451. Min Range: -7.8451
Max Act: 7.3764. Min Act: -0.1700
Data Index: 5725432 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #19