Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4014 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.5893. Min Range: -5.5893
Max Act: 5.5893. Min Act: -0.1700
Data Index: 10038 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5893. Min Range: -5.5893
Max Act: 5.5580. Min Act: -0.1700
Data Index: 7725941 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5893. Min Range: -5.5893
Max Act: 5.5268. Min Act: -0.1700
Data Index: 1013949 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5893. Min Range: -5.5893
Max Act: 5.5268. Min Act: -0.1700
Data Index: 424605 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5893. Min Range: -5.5893
Max Act: 5.4643. Min Act: -0.1700
Data Index: 1191110 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5893. Min Range: -5.5893
Max Act: 5.4643. Min Act: -0.1700
Data Index: 8119336 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5893. Min Range: -5.5893
Max Act: 5.4018. Min Act: -0.1700
Data Index: 530237 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5893. Min Range: -5.5893
Max Act: 5.4330. Min Act: -0.1700
Data Index: 1439704 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5893. Min Range: -5.5893
Max Act: 5.4018. Min Act: -0.1700
Data Index: 3689176 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5893. Min Range: -5.5893
Max Act: 5.4018. Min Act: -0.1700
Data Index: 6959177 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5893. Min Range: -5.5893
Max Act: 5.4018. Min Act: -0.1700
Data Index: 5112939 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5893. Min Range: -5.5893
Max Act: 5.4018. Min Act: -0.1700
Data Index: 2045129 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5893. Min Range: -5.5893
Max Act: 5.3705. Min Act: -0.1700
Data Index: 3982295 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5893. Min Range: -5.5893
Max Act: 5.3705. Min Act: -0.1700
Data Index: 8747669 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5893. Min Range: -5.5893
Max Act: 5.4018. Min Act: -0.1700
Data Index: 2330141 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5893. Min Range: -5.5893
Max Act: 5.3705. Min Act: -0.1700
Data Index: 6741833 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5893. Min Range: -5.5893
Max Act: 5.3705. Min Act: -0.1700
Data Index: 5500418 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5893. Min Range: -5.5893
Max Act: 5.3705. Min Act: -0.1700
Data Index: 7090760 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5893. Min Range: -5.5893
Max Act: 5.3705. Min Act: -0.1700
Data Index: 7381823 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5893. Min Range: -5.5893
Max Act: 5.3080. Min Act: -0.1700
Data Index: 4234067 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #19