Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3970 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.6888. Min Range: -4.6888
Max Act: 4.6888. Min Act: -0.1700
Data Index: 7000440 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6888. Min Range: -4.6888
Max Act: 4.6263. Min Act: -0.1700
Data Index: 2362054 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6888. Min Range: -4.6888
Max Act: 4.5013. Min Act: -0.1700
Data Index: 2952758 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6888. Min Range: -4.6888
Max Act: 4.5326. Min Act: -0.1700
Data Index: 8373764 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6888. Min Range: -4.6888
Max Act: 4.5013. Min Act: -0.1700
Data Index: 3439352 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6888. Min Range: -4.6888
Max Act: 4.5013. Min Act: -0.1700
Data Index: 1096116 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6888. Min Range: -4.6888
Max Act: 4.5013. Min Act: -0.1700
Data Index: 6778066 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6888. Min Range: -4.6888
Max Act: 4.5013. Min Act: -0.1700
Data Index: 5368039 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6888. Min Range: -4.6888
Max Act: 4.4388. Min Act: -0.1700
Data Index: 1604260 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6888. Min Range: -4.6888
Max Act: 4.4701. Min Act: -0.1700
Data Index: 8204767 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6888. Min Range: -4.6888
Max Act: 4.4701. Min Act: -0.1700
Data Index: 8698651 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6888. Min Range: -4.6888
Max Act: 4.4388. Min Act: -0.1700
Data Index: 2362036 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6888. Min Range: -4.6888
Max Act: 4.4388. Min Act: -0.1700
Data Index: 6487343 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6888. Min Range: -4.6888
Max Act: 4.4076. Min Act: -0.1700
Data Index: 4357536 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6888. Min Range: -4.6888
Max Act: 4.4388. Min Act: -0.1700
Data Index: 2355261 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6888. Min Range: -4.6888
Max Act: 4.4076. Min Act: -0.1700
Data Index: 8817424 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6888. Min Range: -4.6888
Max Act: 4.4076. Min Act: -0.1700
Data Index: 2560108 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6888. Min Range: -4.6888
Max Act: 4.4076. Min Act: -0.1700
Data Index: 1740917 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6888. Min Range: -4.6888
Max Act: 4.4076. Min Act: -0.1700
Data Index: 4247176 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6888. Min Range: -4.6888
Max Act: 4.3763. Min Act: -0.1700
Data Index: 7534235 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #19