Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3645 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.1602. Min Range: -3.1602
Max Act: 3.1602. Min Act: -0.1700
Data Index: 6113650 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1602. Min Range: -3.1602
Max Act: 3.0025. Min Act: -0.1700
Data Index: 5266100 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1602. Min Range: -3.1602
Max Act: 2.9709. Min Act: -0.1700
Data Index: 1150951 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1602. Min Range: -3.1602
Max Act: 2.9393. Min Act: -0.1700
Data Index: 546086 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1602. Min Range: -3.1602
Max Act: 2.9076. Min Act: -0.1700
Data Index: 8803578 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1602. Min Range: -3.1602
Max Act: 2.8917. Min Act: -0.1700
Data Index: 8708895 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1602. Min Range: -3.1602
Max Act: 2.8759. Min Act: -0.1700
Data Index: 8633145 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1602. Min Range: -3.1602
Max Act: 2.8441. Min Act: -0.1700
Data Index: 3419267 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1602. Min Range: -3.1602
Max Act: 2.8441. Min Act: -0.1700
Data Index: 3530350 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1602. Min Range: -3.1602
Max Act: 2.8441. Min Act: -0.1700
Data Index: 1911791 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1602. Min Range: -3.1602
Max Act: 2.8282. Min Act: -0.1700
Data Index: 5034383 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1602. Min Range: -3.1602
Max Act: 2.8123. Min Act: -0.1700
Data Index: 7112552 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1602. Min Range: -3.1602
Max Act: 2.8123. Min Act: -0.1700
Data Index: 3275271 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1602. Min Range: -3.1602
Max Act: 2.8123. Min Act: -0.1700
Data Index: 4391108 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1602. Min Range: -3.1602
Max Act: 2.8282. Min Act: -0.1700
Data Index: 7583227 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1602. Min Range: -3.1602
Max Act: 2.7964. Min Act: -0.1700
Data Index: 2529429 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1602. Min Range: -3.1602
Max Act: 2.7804. Min Act: -0.1700
Data Index: 2023164 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1602. Min Range: -3.1602
Max Act: 2.7964. Min Act: -0.1700
Data Index: 7260259 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1602. Min Range: -3.1602
Max Act: 2.7645. Min Act: -0.1700
Data Index: 803347 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1602. Min Range: -3.1602
Max Act: 2.7804. Min Act: -0.1700
Data Index: 2257276 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #19