Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3891 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.3703. Min Range: -5.3703
Max Act: 5.3703. Min Act: -0.1700
Data Index: 8121046 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3703. Min Range: -5.3703
Max Act: 5.2453. Min Act: -0.1700
Data Index: 5615783 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3703. Min Range: -5.3703
Max Act: 5.1203. Min Act: -0.1700
Data Index: 6545707 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3703. Min Range: -5.3703
Max Act: 5.0578. Min Act: -0.1700
Data Index: 5295143 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3703. Min Range: -5.3703
Max Act: 5.0890. Min Act: -0.1700
Data Index: 246296 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3703. Min Range: -5.3703
Max Act: 5.0890. Min Act: -0.1699
Data Index: 4239710 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3703. Min Range: -5.3703
Max Act: 5.0265. Min Act: -0.1700
Data Index: 2113420 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3703. Min Range: -5.3703
Max Act: 4.9640. Min Act: -0.1700
Data Index: 7051916 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3703. Min Range: -5.3703
Max Act: 4.9953. Min Act: -0.1700
Data Index: 1308758 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3703. Min Range: -5.3703
Max Act: 4.9953. Min Act: -0.1700
Data Index: 5869503 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3703. Min Range: -5.3703
Max Act: 4.9640. Min Act: -0.1700
Data Index: 3426374 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3703. Min Range: -5.3703
Max Act: 5.0265. Min Act: -0.1700
Data Index: 1447066 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3703. Min Range: -5.3703
Max Act: 4.9953. Min Act: -0.1700
Data Index: 5349663 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3703. Min Range: -5.3703
Max Act: 4.9640. Min Act: -0.1700
Data Index: 2547538 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3703. Min Range: -5.3703
Max Act: 4.9640. Min Act: -0.1700
Data Index: 5617956 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3703. Min Range: -5.3703
Max Act: 4.9640. Min Act: -0.1700
Data Index: 5155984 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3703. Min Range: -5.3703
Max Act: 4.9328. Min Act: -0.1700
Data Index: 2318524 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3703. Min Range: -5.3703
Max Act: 4.9640. Min Act: -0.1700
Data Index: 2801126 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3703. Min Range: -5.3703
Max Act: 4.9640. Min Act: -0.1700
Data Index: 8470543 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3703. Min Range: -5.3703
Max Act: 4.9328. Min Act: -0.1700
Data Index: 8429900 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #19