Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3028 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3575. Min Range: -8.3575
Max Act: 8.3575. Min Act: -0.1700
Data Index: 7058701 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3575. Min Range: -8.3575
Max Act: 8.3575. Min Act: -0.1700
Data Index: 8087762 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3575. Min Range: -8.3575
Max Act: 8.1387. Min Act: -0.1700
Data Index: 5236758 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3575. Min Range: -8.3575
Max Act: 8.0762. Min Act: -0.1700
Data Index: 8589743 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3575. Min Range: -8.3575
Max Act: 8.0450. Min Act: -0.1700
Data Index: 5173872 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3575. Min Range: -8.3575
Max Act: 8.0450. Min Act: -0.1700
Data Index: 1959481 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3575. Min Range: -8.3575
Max Act: 7.8887. Min Act: -0.1700
Data Index: 4175627 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3575. Min Range: -8.3575
Max Act: 7.8887. Min Act: -0.1700
Data Index: 2938228 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3575. Min Range: -8.3575
Max Act: 7.8887. Min Act: -0.1700
Data Index: 3204786 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3575. Min Range: -8.3575
Max Act: 7.8575. Min Act: -0.1700
Data Index: 4887901 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3575. Min Range: -8.3575
Max Act: 7.8575. Min Act: -0.1700
Data Index: 2578113 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3575. Min Range: -8.3575
Max Act: 7.8262. Min Act: -0.1700
Data Index: 4887903 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3575. Min Range: -8.3575
Max Act: 7.7950. Min Act: -0.1700
Data Index: 6016302 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3575. Min Range: -8.3575
Max Act: 7.7950. Min Act: -0.1700
Data Index: 8615750 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3575. Min Range: -8.3575
Max Act: 7.7637. Min Act: -0.1700
Data Index: 2681821 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3575. Min Range: -8.3575
Max Act: 7.7637. Min Act: -0.1700
Data Index: 4332153 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3575. Min Range: -8.3575
Max Act: 7.7637. Min Act: -0.1700
Data Index: 8589748 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3575. Min Range: -8.3575
Max Act: 7.7325. Min Act: -0.1700
Data Index: 4435471 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3575. Min Range: -8.3575
Max Act: 7.7325. Min Act: -0.1700
Data Index: 6484034 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3575. Min Range: -8.3575
Max Act: 7.7012. Min Act: -0.1700
Data Index: 506533 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #19