Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4138 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.7850. Min Range: -6.7850
Max Act: 6.7850. Min Act: -0.1700
Data Index: 2162767 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7850. Min Range: -6.7850
Max Act: 6.6913. Min Act: -0.1700
Data Index: 3700807 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7850. Min Range: -6.7850
Max Act: 6.6288. Min Act: -0.1700
Data Index: 1501969 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7850. Min Range: -6.7850
Max Act: 6.5975. Min Act: -0.1700
Data Index: 1703908 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7850. Min Range: -6.7850
Max Act: 6.5350. Min Act: -0.1700
Data Index: 1417368 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7850. Min Range: -6.7850
Max Act: 6.4413. Min Act: -0.1700
Data Index: 1475529 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7850. Min Range: -6.7850
Max Act: 6.4413. Min Act: -0.1700
Data Index: 159844 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7850. Min Range: -6.7850
Max Act: 6.4100. Min Act: -0.1700
Data Index: 5733048 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7850. Min Range: -6.7850
Max Act: 6.3788. Min Act: -0.1700
Data Index: 8727504 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7850. Min Range: -6.7850
Max Act: 6.3788. Min Act: -0.1700
Data Index: 232494 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7850. Min Range: -6.7850
Max Act: 6.3475. Min Act: -0.1700
Data Index: 1747172 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7850. Min Range: -6.7850
Max Act: 6.3163. Min Act: -0.1700
Data Index: 6703684 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7850. Min Range: -6.7850
Max Act: 6.3163. Min Act: -0.1700
Data Index: 6364149 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7850. Min Range: -6.7850
Max Act: 6.2850. Min Act: -0.1700
Data Index: 6924965 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7850. Min Range: -6.7850
Max Act: 6.2850. Min Act: -0.1700
Data Index: 6218856 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7850. Min Range: -6.7850
Max Act: 6.2850. Min Act: -0.1700
Data Index: 6558451 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7850. Min Range: -6.7850
Max Act: 6.2538. Min Act: -0.1700
Data Index: 8198498 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7850. Min Range: -6.7850
Max Act: 6.2225. Min Act: -0.1700
Data Index: 1043895 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7850. Min Range: -6.7850
Max Act: 6.2225. Min Act: -0.1700
Data Index: 597494 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7850. Min Range: -6.7850
Max Act: 6.1913. Min Act: -0.1700
Data Index: 5585852 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #19