Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2726 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.2049. Min Range: -7.2049
Max Act: 7.2049. Min Act: -0.1700
Data Index: 1280383 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2049. Min Range: -7.2049
Max Act: 6.9237. Min Act: -0.1700
Data Index: 454558 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2049. Min Range: -7.2049
Max Act: 6.9237. Min Act: -0.1700
Data Index: 8408822 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2049. Min Range: -7.2049
Max Act: 6.8299. Min Act: -0.1700
Data Index: 6323512 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2049. Min Range: -7.2049
Max Act: 6.4862. Min Act: -0.1700
Data Index: 6971084 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2049. Min Range: -7.2049
Max Act: 6.4862. Min Act: -0.1700
Data Index: 147193 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2049. Min Range: -7.2049
Max Act: 6.4862. Min Act: -0.1700
Data Index: 4320490 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2049. Min Range: -7.2049
Max Act: 6.4237. Min Act: -0.1700
Data Index: 4283011 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2049. Min Range: -7.2049
Max Act: 6.4237. Min Act: -0.1700
Data Index: 7317417 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2049. Min Range: -7.2049
Max Act: 6.3924. Min Act: -0.1700
Data Index: 1607401 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2049. Min Range: -7.2049
Max Act: 6.3612. Min Act: -0.1700
Data Index: 8710759 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2049. Min Range: -7.2049
Max Act: 6.3299. Min Act: -0.1700
Data Index: 8578672 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2049. Min Range: -7.2049
Max Act: 6.2987. Min Act: -0.1700
Data Index: 2551781 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2049. Min Range: -7.2049
Max Act: 6.3299. Min Act: -0.1700
Data Index: 1830946 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2049. Min Range: -7.2049
Max Act: 6.2987. Min Act: -0.1700
Data Index: 815899 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2049. Min Range: -7.2049
Max Act: 6.2987. Min Act: -0.1700
Data Index: 6112590 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2049. Min Range: -7.2049
Max Act: 6.2674. Min Act: -0.1700
Data Index: 7854457 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2049. Min Range: -7.2049
Max Act: 6.2362. Min Act: -0.1700
Data Index: 4253931 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2049. Min Range: -7.2049
Max Act: 6.2674. Min Act: -0.1700
Data Index: 4005129 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2049. Min Range: -7.2049
Max Act: 6.2362. Min Act: -0.1700
Data Index: 2687075 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #19