Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 749 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.2106. Min Range: -4.2106
Max Act: 4.2106. Min Act: -0.1700
Data Index: 3318787 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2106. Min Range: -4.2106
Max Act: 4.2106. Min Act: -0.1700
Data Index: 1174560 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2106. Min Range: -4.2106
Max Act: 4.1794. Min Act: -0.1700
Data Index: 1862667 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2106. Min Range: -4.2106
Max Act: 4.1169. Min Act: -0.1700
Data Index: 4669915 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2106. Min Range: -4.2106
Max Act: 4.1169. Min Act: -0.1700
Data Index: 6841943 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2106. Min Range: -4.2106
Max Act: 4.0856. Min Act: -0.1700
Data Index: 8502419 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2106. Min Range: -4.2106
Max Act: 4.0231. Min Act: -0.1700
Data Index: 829747 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2106. Min Range: -4.2106
Max Act: 3.9293. Min Act: -0.1700
Data Index: 123318 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2106. Min Range: -4.2106
Max Act: 3.9606. Min Act: -0.1700
Data Index: 6581702 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2106. Min Range: -4.2106
Max Act: 3.9606. Min Act: -0.1700
Data Index: 82324 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2106. Min Range: -4.2106
Max Act: 3.9293. Min Act: -0.1700
Data Index: 3627519 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2106. Min Range: -4.2106
Max Act: 3.9293. Min Act: -0.1700
Data Index: 7726616 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2106. Min Range: -4.2106
Max Act: 3.9293. Min Act: -0.1700
Data Index: 4310612 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2106. Min Range: -4.2106
Max Act: 3.8981. Min Act: -0.1700
Data Index: 2943417 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2106. Min Range: -4.2106
Max Act: 3.8981. Min Act: -0.1700
Data Index: 5155028 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2106. Min Range: -4.2106
Max Act: 3.8668. Min Act: -0.1700
Data Index: 5795358 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2106. Min Range: -4.2106
Max Act: 3.8668. Min Act: -0.1700
Data Index: 2797059 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2106. Min Range: -4.2106
Max Act: 3.8981. Min Act: -0.1700
Data Index: 7116839 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2106. Min Range: -4.2106
Max Act: 3.9293. Min Act: -0.1700
Data Index: 795595 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2106. Min Range: -4.2106
Max Act: 3.8668. Min Act: -0.1700
Data Index: 2137046 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #19