Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2413 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.3217. Min Range: -3.3217
Max Act: 3.3217. Min Act: -0.1700
Data Index: 270829 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3217. Min Range: -3.3217
Max Act: 3.2904. Min Act: -0.1700
Data Index: 8541291 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3217. Min Range: -3.3217
Max Act: 3.2275. Min Act: -0.1700
Data Index: 8585547 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3217. Min Range: -3.3217
Max Act: 3.1803. Min Act: -0.1700
Data Index: 3992139 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3217. Min Range: -3.3217
Max Act: 3.1803. Min Act: -0.1700
Data Index: 7840775 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3217. Min Range: -3.3217
Max Act: 3.1803. Min Act: -0.1700
Data Index: 537804 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3217. Min Range: -3.3217
Max Act: 3.1803. Min Act: -0.1700
Data Index: 3671374 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3217. Min Range: -3.3217
Max Act: 3.1646. Min Act: -0.1700
Data Index: 3501795 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3217. Min Range: -3.3217
Max Act: 3.1646. Min Act: -0.1700
Data Index: 8353456 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3217. Min Range: -3.3217
Max Act: 3.1646. Min Act: -0.1700
Data Index: 701830 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3217. Min Range: -3.3217
Max Act: 3.1489. Min Act: -0.1700
Data Index: 1852109 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3217. Min Range: -3.3217
Max Act: 3.1489. Min Act: -0.1700
Data Index: 2906445 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3217. Min Range: -3.3217
Max Act: 3.1331. Min Act: -0.1700
Data Index: 5517299 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3217. Min Range: -3.3217
Max Act: 3.1331. Min Act: -0.1700
Data Index: 2166905 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3217. Min Range: -3.3217
Max Act: 3.1331. Min Act: -0.1700
Data Index: 5322638 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3217. Min Range: -3.3217
Max Act: 3.1174. Min Act: -0.1700
Data Index: 5045650 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3217. Min Range: -3.3217
Max Act: 3.1174. Min Act: -0.1700
Data Index: 3616046 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3217. Min Range: -3.3217
Max Act: 3.1174. Min Act: -0.1700
Data Index: 6789235 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3217. Min Range: -3.3217
Max Act: 3.1174. Min Act: -0.1700
Data Index: 7840773 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3217. Min Range: -3.3217
Max Act: 3.1174. Min Act: -0.1700
Data Index: 6072680 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #19