Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1935 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0727. Min Range: -4.0727
Max Act: 4.0727. Min Act: -0.1700
Data Index: 2608205 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0727. Min Range: -4.0727
Max Act: 3.9790. Min Act: -0.1700
Data Index: 2606663 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0727. Min Range: -4.0727
Max Act: 3.9477. Min Act: -0.1700
Data Index: 6443142 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0727. Min Range: -4.0727
Max Act: 3.8852. Min Act: -0.1700
Data Index: 1527142 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0727. Min Range: -4.0727
Max Act: 3.8852. Min Act: -0.1700
Data Index: 362066 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0727. Min Range: -4.0727
Max Act: 3.9164. Min Act: -0.1700
Data Index: 5835071 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0727. Min Range: -4.0727
Max Act: 3.8852. Min Act: -0.1700
Data Index: 3707290 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0727. Min Range: -4.0727
Max Act: 3.8852. Min Act: -0.1700
Data Index: 4338248 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0727. Min Range: -4.0727
Max Act: 3.8539. Min Act: -0.1700
Data Index: 1895941 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0727. Min Range: -4.0727
Max Act: 3.8539. Min Act: -0.1700
Data Index: 5564504 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0727. Min Range: -4.0727
Max Act: 3.8226. Min Act: -0.1700
Data Index: 8824104 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0727. Min Range: -4.0727
Max Act: 3.7757. Min Act: -0.1700
Data Index: 8457453 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0727. Min Range: -4.0727
Max Act: 3.7757. Min Act: -0.1700
Data Index: 5147560 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0727. Min Range: -4.0727
Max Act: 3.7601. Min Act: -0.1700
Data Index: 4499005 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0727. Min Range: -4.0727
Max Act: 3.7601. Min Act: -0.1700
Data Index: 6482233 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0727. Min Range: -4.0727
Max Act: 3.7288. Min Act: -0.1700
Data Index: 3329569 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0727. Min Range: -4.0727
Max Act: 3.7132. Min Act: -0.1700
Data Index: 29890 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0727. Min Range: -4.0727
Max Act: 3.7288. Min Act: -0.1700
Data Index: 2724719 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0727. Min Range: -4.0727
Max Act: 3.7132. Min Act: -0.1700
Data Index: 499493 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0727. Min Range: -4.0727
Max Act: 3.7132. Min Act: -0.1700
Data Index: 3778606 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #19