Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3398 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9843. Min Range: -4.9843
Max Act: 4.9843. Min Act: -0.1700
Data Index: 7395226 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9843. Min Range: -4.9843
Max Act: 4.9531. Min Act: -0.1700
Data Index: 5657429 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9843. Min Range: -4.9843
Max Act: 4.9218. Min Act: -0.1700
Data Index: 1670368 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9843. Min Range: -4.9843
Max Act: 4.9531. Min Act: -0.1700
Data Index: 4770031 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9843. Min Range: -4.9843
Max Act: 4.9531. Min Act: -0.1700
Data Index: 6741385 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9843. Min Range: -4.9843
Max Act: 4.8906. Min Act: -0.1700
Data Index: 5047382 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9843. Min Range: -4.9843
Max Act: 4.8593. Min Act: -0.1700
Data Index: 8465941 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9843. Min Range: -4.9843
Max Act: 4.8593. Min Act: -0.1700
Data Index: 3656271 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9843. Min Range: -4.9843
Max Act: 4.8281. Min Act: -0.1700
Data Index: 7647068 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9843. Min Range: -4.9843
Max Act: 4.8281. Min Act: -0.1700
Data Index: 7650136 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9843. Min Range: -4.9843
Max Act: 4.8281. Min Act: -0.1700
Data Index: 3639148 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9843. Min Range: -4.9843
Max Act: 4.7968. Min Act: -0.1700
Data Index: 29715 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9843. Min Range: -4.9843
Max Act: 4.7968. Min Act: -0.1700
Data Index: 2279417 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9843. Min Range: -4.9843
Max Act: 4.7656. Min Act: -0.1700
Data Index: 737707 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9843. Min Range: -4.9843
Max Act: 4.7343. Min Act: -0.1700
Data Index: 5219785 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9843. Min Range: -4.9843
Max Act: 4.7343. Min Act: -0.1700
Data Index: 1239615 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9843. Min Range: -4.9843
Max Act: 4.7343. Min Act: -0.1700
Data Index: 6833292 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9843. Min Range: -4.9843
Max Act: 4.6718. Min Act: -0.1700
Data Index: 3510249 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9843. Min Range: -4.9843
Max Act: 4.6718. Min Act: -0.1700
Data Index: 4799459 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9843. Min Range: -4.9843
Max Act: 4.6718. Min Act: -0.1700
Data Index: 1724724 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #19