Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5114 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.1127. Min Range: -3.1127
Max Act: 3.1127. Min Act: -0.1700
Data Index: 4954082 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1127. Min Range: -3.1127
Max Act: 2.8755. Min Act: -0.1700
Data Index: 3576979 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1127. Min Range: -3.1127
Max Act: 2.8597. Min Act: -0.1700
Data Index: 6901932 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1127. Min Range: -3.1127
Max Act: 2.8597. Min Act: -0.1700
Data Index: 3144712 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1127. Min Range: -3.1127
Max Act: 2.8279. Min Act: -0.1700
Data Index: 5903288 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1127. Min Range: -3.1127
Max Act: 2.8120. Min Act: -0.1700
Data Index: 7739074 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1127. Min Range: -3.1127
Max Act: 2.8120. Min Act: -0.1700
Data Index: 253999 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1127. Min Range: -3.1127
Max Act: 2.7960. Min Act: -0.1700
Data Index: 4184754 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1127. Min Range: -3.1127
Max Act: 2.8120. Min Act: -0.1700
Data Index: 3689014 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1127. Min Range: -3.1127
Max Act: 2.7642. Min Act: -0.1700
Data Index: 7105998 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1127. Min Range: -3.1127
Max Act: 2.7801. Min Act: -0.1699
Data Index: 3083774 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1127. Min Range: -3.1127
Max Act: 2.7642. Min Act: -0.1700
Data Index: 1637820 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1127. Min Range: -3.1127
Max Act: 2.7642. Min Act: -0.1700
Data Index: 5408457 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1127. Min Range: -3.1127
Max Act: 2.7642. Min Act: -0.1700
Data Index: 3402129 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1127. Min Range: -3.1127
Max Act: 2.7322. Min Act: -0.1700
Data Index: 678626 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1127. Min Range: -3.1127
Max Act: 2.7322. Min Act: -0.1700
Data Index: 424847 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1127. Min Range: -3.1127
Max Act: 2.7322. Min Act: -0.1700
Data Index: 4103351 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1127. Min Range: -3.1127
Max Act: 2.7322. Min Act: -0.1700
Data Index: 6824683 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1127. Min Range: -3.1127
Max Act: 2.7163. Min Act: -0.1700
Data Index: 3812494 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1127. Min Range: -3.1127
Max Act: 2.7163. Min Act: -0.1700
Data Index: 3513997 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #19