Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer
Dataset: Open Web Text
Neuron 2369 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-small')
Text #0
Max Range: 4.7756. Min Range: -4.7756
Max Act: 4.7756. Min Act: -0.1700
Data Index: 7379809 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7756. Min Range: -4.7756
Max Act: 4.6506. Min Act: -0.1700
Data Index: 1692554 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7756. Min Range: -4.7756
Max Act: 4.6506. Min Act: -0.1700
Data Index: 5507524 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7756. Min Range: -4.7756
Max Act: 4.5881. Min Act: -0.1700
Data Index: 5593972 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7756. Min Range: -4.7756
Max Act: 4.5881. Min Act: -0.1700
Data Index: 5769167 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7756. Min Range: -4.7756
Max Act: 4.5569. Min Act: -0.1700
Data Index: 465509 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7756. Min Range: -4.7756
Max Act: 4.5569. Min Act: -0.1700
Data Index: 4935471 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7756. Min Range: -4.7756
Max Act: 4.5569. Min Act: -0.1700
Data Index: 3711290 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7756. Min Range: -4.7756
Max Act: 4.5256. Min Act: -0.1700
Data Index: 6392605 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7756. Min Range: -4.7756
Max Act: 4.5256. Min Act: -0.1700
Data Index: 1480152 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7756. Min Range: -4.7756
Max Act: 4.4944. Min Act: -0.1700
Data Index: 2581132 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7756. Min Range: -4.7756
Max Act: 4.4944. Min Act: -0.1700
Data Index: 2458222 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7756. Min Range: -4.7756
Max Act: 4.4631. Min Act: -0.1700
Data Index: 8041362 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7756. Min Range: -4.7756
Max Act: 4.4631. Min Act: -0.1700
Data Index: 7938426 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7756. Min Range: -4.7756
Max Act: 4.4319. Min Act: -0.1700
Data Index: 5122998 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7756. Min Range: -4.7756
Max Act: 4.4631. Min Act: -0.1700
Data Index: 8248969 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7756. Min Range: -4.7756
Max Act: 4.4631. Min Act: -0.1700
Data Index: 5588147 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7756. Min Range: -4.7756
Max Act: 4.4319. Min Act: -0.1700
Data Index: 7851550 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7756. Min Range: -4.7756
Max Act: 4.4319. Min Act: -0.1700
Data Index: 7276776 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7756. Min Range: -4.7756
Max Act: 4.4006. Min Act: -0.1700
Data Index: 804524 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #19