Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 852 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8075. Min Range: -6.8075
Max Act: 6.8075. Min Act: -0.1700
Data Index: 6166028 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8075. Min Range: -6.8075
Max Act: 6.5575. Min Act: -0.1700
Data Index: 3130226 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8075. Min Range: -6.8075
Max Act: 6.3700. Min Act: -0.1700
Data Index: 6063715 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8075. Min Range: -6.8075
Max Act: 6.2137. Min Act: -0.1700
Data Index: 1039118 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8075. Min Range: -6.8075
Max Act: 6.2137. Min Act: -0.1700
Data Index: 7624012 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8075. Min Range: -6.8075
Max Act: 6.1825. Min Act: -0.1700
Data Index: 1924828 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8075. Min Range: -6.8075
Max Act: 6.1512. Min Act: -0.1700
Data Index: 2643625 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8075. Min Range: -6.8075
Max Act: 6.1512. Min Act: -0.1700
Data Index: 5665146 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8075. Min Range: -6.8075
Max Act: 6.0262. Min Act: -0.1700
Data Index: 8294657 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8075. Min Range: -6.8075
Max Act: 6.0575. Min Act: -0.1700
Data Index: 223390 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8075. Min Range: -6.8075
Max Act: 6.0575. Min Act: -0.1700
Data Index: 1232021 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8075. Min Range: -6.8075
Max Act: 5.9950. Min Act: -0.1700
Data Index: 8809409 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8075. Min Range: -6.8075
Max Act: 5.9950. Min Act: -0.1700
Data Index: 3623597 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8075. Min Range: -6.8075
Max Act: 5.9637. Min Act: -0.1700
Data Index: 4332625 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8075. Min Range: -6.8075
Max Act: 5.9637. Min Act: -0.1700
Data Index: 8380081 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8075. Min Range: -6.8075
Max Act: 5.9637. Min Act: -0.1700
Data Index: 6238072 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8075. Min Range: -6.8075
Max Act: 5.9325. Min Act: -0.1700
Data Index: 1676080 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8075. Min Range: -6.8075
Max Act: 5.9325. Min Act: -0.1700
Data Index: 15971 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8075. Min Range: -6.8075
Max Act: 5.9012. Min Act: -0.1700
Data Index: 5802195 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8075. Min Range: -6.8075
Max Act: 5.9012. Min Act: -0.1700
Data Index: 5069663 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #19