Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 368 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.7922. Min Range: -5.7922
Max Act: 5.7922. Min Act: -0.1700
Data Index: 821473 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7922. Min Range: -5.7922
Max Act: 5.4797. Min Act: -0.1700
Data Index: 5179089 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7922. Min Range: -5.7922
Max Act: 5.4797. Min Act: -0.1700
Data Index: 5547549 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7922. Min Range: -5.7922
Max Act: 5.4797. Min Act: -0.1700
Data Index: 5599163 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7922. Min Range: -5.7922
Max Act: 5.4172. Min Act: -0.1700
Data Index: 189362 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7922. Min Range: -5.7922
Max Act: 5.3859. Min Act: -0.1700
Data Index: 5364246 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7922. Min Range: -5.7922
Max Act: 5.3859. Min Act: -0.1700
Data Index: 7912014 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7922. Min Range: -5.7922
Max Act: 5.3547. Min Act: -0.1700
Data Index: 7306889 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7922. Min Range: -5.7922
Max Act: 5.3859. Min Act: -0.1700
Data Index: 1394223 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7922. Min Range: -5.7922
Max Act: 5.3859. Min Act: -0.1700
Data Index: 6996674 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7922. Min Range: -5.7922
Max Act: 5.3547. Min Act: -0.1700
Data Index: 350955 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7922. Min Range: -5.7922
Max Act: 5.3234. Min Act: -0.1700
Data Index: 5657649 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7922. Min Range: -5.7922
Max Act: 5.3234. Min Act: -0.1700
Data Index: 8623205 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7922. Min Range: -5.7922
Max Act: 5.2922. Min Act: -0.1700
Data Index: 8352089 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7922. Min Range: -5.7922
Max Act: 5.2922. Min Act: -0.1700
Data Index: 1474853 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7922. Min Range: -5.7922
Max Act: 5.2609. Min Act: -0.1700
Data Index: 4708345 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7922. Min Range: -5.7922
Max Act: 5.2922. Min Act: -0.1699
Data Index: 4452592 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7922. Min Range: -5.7922
Max Act: 5.2922. Min Act: -0.1700
Data Index: 6687216 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7922. Min Range: -5.7922
Max Act: 5.2922. Min Act: -0.1698
Data Index: 6584499 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7922. Min Range: -5.7922
Max Act: 5.2609. Min Act: -0.1700
Data Index: 1213876 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #19