Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6097 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4774. Min Range: -5.4774
Max Act: 5.4774. Min Act: -0.1700
Data Index: 2200427 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4774. Min Range: -5.4774
Max Act: 5.2899. Min Act: -0.1700
Data Index: 104362 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4774. Min Range: -5.4774
Max Act: 5.3212. Min Act: -0.1700
Data Index: 2370246 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4774. Min Range: -5.4774
Max Act: 5.3212. Min Act: -0.1700
Data Index: 6517513 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4774. Min Range: -5.4774
Max Act: 5.3212. Min Act: -0.1700
Data Index: 8113211 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4774. Min Range: -5.4774
Max Act: 5.2899. Min Act: -0.1700
Data Index: 6501673 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4774. Min Range: -5.4774
Max Act: 5.2899. Min Act: -0.1700
Data Index: 6481861 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4774. Min Range: -5.4774
Max Act: 5.2899. Min Act: -0.1700
Data Index: 929717 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4774. Min Range: -5.4774
Max Act: 5.2274. Min Act: -0.1700
Data Index: 40216 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4774. Min Range: -5.4774
Max Act: 5.2274. Min Act: -0.1700
Data Index: 4374544 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4774. Min Range: -5.4774
Max Act: 5.2274. Min Act: -0.1700
Data Index: 6545968 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4774. Min Range: -5.4774
Max Act: 5.1962. Min Act: -0.1700
Data Index: 3381357 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4774. Min Range: -5.4774
Max Act: 5.2587. Min Act: -0.1700
Data Index: 8541771 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4774. Min Range: -5.4774
Max Act: 5.2274. Min Act: -0.1700
Data Index: 2942948 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4774. Min Range: -5.4774
Max Act: 5.2274. Min Act: -0.1700
Data Index: 3460005 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4774. Min Range: -5.4774
Max Act: 5.1962. Min Act: -0.1700
Data Index: 3846237 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4774. Min Range: -5.4774
Max Act: 5.1649. Min Act: -0.1700
Data Index: 7323035 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4774. Min Range: -5.4774
Max Act: 5.1649. Min Act: -0.1700
Data Index: 3370589 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4774. Min Range: -5.4774
Max Act: 5.1649. Min Act: -0.1700
Data Index: 913081 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4774. Min Range: -5.4774
Max Act: 5.1649. Min Act: -0.1700
Data Index: 4937265 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #19