Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5848 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8126. Min Range: -6.8126
Max Act: 6.8126. Min Act: -0.1700
Data Index: 4484639 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8126. Min Range: -6.8126
Max Act: 6.6876. Min Act: -0.1700
Data Index: 8442908 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8126. Min Range: -6.8126
Max Act: 6.6876. Min Act: -0.1700
Data Index: 6090050 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8126. Min Range: -6.8126
Max Act: 6.5626. Min Act: -0.1700
Data Index: 8119460 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8126. Min Range: -6.8126
Max Act: 6.5626. Min Act: -0.1700
Data Index: 2448966 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8126. Min Range: -6.8126
Max Act: 6.4688. Min Act: -0.1700
Data Index: 7855131 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8126. Min Range: -6.8126
Max Act: 6.4376. Min Act: -0.1700
Data Index: 3449221 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8126. Min Range: -6.8126
Max Act: 6.4063. Min Act: -0.1700
Data Index: 545095 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8126. Min Range: -6.8126
Max Act: 6.3126. Min Act: -0.1700
Data Index: 7094149 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8126. Min Range: -6.8126
Max Act: 6.3126. Min Act: -0.1700
Data Index: 439586 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8126. Min Range: -6.8126
Max Act: 6.3126. Min Act: -0.1700
Data Index: 3928790 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8126. Min Range: -6.8126
Max Act: 6.3126. Min Act: -0.1700
Data Index: 5125106 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8126. Min Range: -6.8126
Max Act: 6.2813. Min Act: -0.1700
Data Index: 3216948 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8126. Min Range: -6.8126
Max Act: 6.2813. Min Act: -0.1700
Data Index: 2926961 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8126. Min Range: -6.8126
Max Act: 6.2813. Min Act: -0.1700
Data Index: 1026491 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8126. Min Range: -6.8126
Max Act: 6.2188. Min Act: -0.1700
Data Index: 6096378 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8126. Min Range: -6.8126
Max Act: 6.1563. Min Act: -0.1700
Data Index: 3165362 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8126. Min Range: -6.8126
Max Act: 6.1876. Min Act: -0.1700
Data Index: 5338061 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8126. Min Range: -6.8126
Max Act: 6.2188. Min Act: -0.1700
Data Index: 3106961 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8126. Min Range: -6.8126
Max Act: 6.1563. Min Act: -0.1700
Data Index: 4511517 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #19