Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4715 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.3378. Min Range: -3.3378
Max Act: 3.3378. Min Act: -0.1700
Data Index: 6908243 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3378. Min Range: -3.3378
Max Act: 3.3378. Min Act: -0.1700
Data Index: 3006754 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3378. Min Range: -3.3378
Max Act: 3.3065. Min Act: -0.1700
Data Index: 706812 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3378. Min Range: -3.3378
Max Act: 3.2908. Min Act: -0.1700
Data Index: 3846104 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3378. Min Range: -3.3378
Max Act: 3.2751. Min Act: -0.1700
Data Index: 8050332 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3378. Min Range: -3.3378
Max Act: 3.2751. Min Act: -0.1700
Data Index: 1476647 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3378. Min Range: -3.3378
Max Act: 3.2751. Min Act: -0.1700
Data Index: 6857113 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3378. Min Range: -3.3378
Max Act: 3.2593. Min Act: -0.1700
Data Index: 1078218 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3378. Min Range: -3.3378
Max Act: 3.2751. Min Act: -0.1700
Data Index: 4142513 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3378. Min Range: -3.3378
Max Act: 3.2593. Min Act: -0.1700
Data Index: 7516020 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3378. Min Range: -3.3378
Max Act: 3.2593. Min Act: -0.1700
Data Index: 4750579 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3378. Min Range: -3.3378
Max Act: 3.2436. Min Act: -0.1700
Data Index: 3244568 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3378. Min Range: -3.3378
Max Act: 3.2436. Min Act: -0.1700
Data Index: 8674572 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3378. Min Range: -3.3378
Max Act: 3.2279. Min Act: -0.1700
Data Index: 3320829 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3378. Min Range: -3.3378
Max Act: 3.2436. Min Act: -0.1700
Data Index: 8114374 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3378. Min Range: -3.3378
Max Act: 3.2279. Min Act: -0.1700
Data Index: 2334390 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3378. Min Range: -3.3378
Max Act: 3.2122. Min Act: -0.1700
Data Index: 561263 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3378. Min Range: -3.3378
Max Act: 3.2279. Min Act: -0.1700
Data Index: 7661187 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3378. Min Range: -3.3378
Max Act: 3.2279. Min Act: -0.1700
Data Index: 7863284 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3378. Min Range: -3.3378
Max Act: 3.2279. Min Act: -0.1700
Data Index: 8048105 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #19