Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6084 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.3071. Min Range: -3.3071
Max Act: 3.3071. Min Act: -0.1700
Data Index: 7639154 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3071. Min Range: -3.3071
Max Act: 3.3071. Min Act: -0.1700
Data Index: 7683875 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3071. Min Range: -3.3071
Max Act: 3.3071. Min Act: -0.1700
Data Index: 2284095 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3071. Min Range: -3.3071
Max Act: 3.2600. Min Act: -0.1700
Data Index: 7343598 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3071. Min Range: -3.3071
Max Act: 3.2443. Min Act: -0.1700
Data Index: 5911284 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3071. Min Range: -3.3071
Max Act: 3.2286. Min Act: -0.1700
Data Index: 2652082 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3071. Min Range: -3.3071
Max Act: 3.2286. Min Act: -0.1700
Data Index: 8591563 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3071. Min Range: -3.3071
Max Act: 3.2128. Min Act: -0.1700
Data Index: 2252728 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3071. Min Range: -3.3071
Max Act: 3.2128. Min Act: -0.1700
Data Index: 2320159 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3071. Min Range: -3.3071
Max Act: 3.1971. Min Act: -0.1700
Data Index: 3085752 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3071. Min Range: -3.3071
Max Act: 3.1814. Min Act: -0.1700
Data Index: 7322562 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3071. Min Range: -3.3071
Max Act: 3.1814. Min Act: -0.1700
Data Index: 2762359 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3071. Min Range: -3.3071
Max Act: 3.1814. Min Act: -0.1700
Data Index: 2901961 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3071. Min Range: -3.3071
Max Act: 3.1657. Min Act: -0.1700
Data Index: 7343316 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3071. Min Range: -3.3071
Max Act: 3.1657. Min Act: -0.1700
Data Index: 4909362 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3071. Min Range: -3.3071
Max Act: 3.1499. Min Act: -0.1700
Data Index: 867331 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3071. Min Range: -3.3071
Max Act: 3.1657. Min Act: -0.1700
Data Index: 2702642 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3071. Min Range: -3.3071
Max Act: 3.1499. Min Act: -0.1700
Data Index: 1613787 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3071. Min Range: -3.3071
Max Act: 3.1499. Min Act: -0.1700
Data Index: 4372143 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3071. Min Range: -3.3071
Max Act: 3.1499. Min Act: -0.1700
Data Index: 655849 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #19