Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2271 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.1888. Min Range: -3.1888
Max Act: 3.1730. Min Act: -0.1700
Data Index: 84165 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1888. Min Range: -3.1888
Max Act: 3.1888. Min Act: -0.1700
Data Index: 1851899 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1888. Min Range: -3.1888
Max Act: 3.1101. Min Act: -0.1700
Data Index: 3521882 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1888. Min Range: -3.1888
Max Act: 3.1101. Min Act: -0.1700
Data Index: 3469504 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1888. Min Range: -3.1888
Max Act: 3.0628. Min Act: -0.1700
Data Index: 6694098 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1888. Min Range: -3.1888
Max Act: 3.0628. Min Act: -0.1700
Data Index: 6335145 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1888. Min Range: -3.1888
Max Act: 3.0154. Min Act: -0.1700
Data Index: 368922 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1888. Min Range: -3.1888
Max Act: 3.0312. Min Act: -0.1700
Data Index: 402591 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1888. Min Range: -3.1888
Max Act: 3.0154. Min Act: -0.1700
Data Index: 1741574 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1888. Min Range: -3.1888
Max Act: 3.0154. Min Act: -0.1700
Data Index: 3817309 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1888. Min Range: -3.1888
Max Act: 2.9996. Min Act: -0.1700
Data Index: 84166 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1888. Min Range: -3.1888
Max Act: 3.0154. Min Act: -0.1700
Data Index: 3534987 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1888. Min Range: -3.1888
Max Act: 2.9838. Min Act: -0.1700
Data Index: 5387175 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1888. Min Range: -3.1888
Max Act: 2.9838. Min Act: -0.1700
Data Index: 8080432 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1888. Min Range: -3.1888
Max Act: 2.9838. Min Act: -0.1700
Data Index: 1212197 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1888. Min Range: -3.1888
Max Act: 2.9838. Min Act: -0.1700
Data Index: 6188814 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1888. Min Range: -3.1888
Max Act: 2.9838. Min Act: -0.1700
Data Index: 883266 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1888. Min Range: -3.1888
Max Act: 2.9838. Min Act: -0.1700
Data Index: 2719672 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1888. Min Range: -3.1888
Max Act: 2.9680. Min Act: -0.1700
Data Index: 6571797 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1888. Min Range: -3.1888
Max Act: 2.9522. Min Act: -0.1700
Data Index: 2575411 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #19