Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2843 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.6683. Min Range: -8.6683
Max Act: 8.6683. Min Act: -0.1700
Data Index: 3705515 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6683. Min Range: -8.6683
Max Act: 8.6683. Min Act: -0.1700
Data Index: 6290420 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6683. Min Range: -8.6683
Max Act: 8.6058. Min Act: -0.1700
Data Index: 2664450 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6683. Min Range: -8.6683
Max Act: 8.5433. Min Act: -0.1700
Data Index: 632050 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6683. Min Range: -8.6683
Max Act: 8.4808. Min Act: -0.1700
Data Index: 4979670 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6683. Min Range: -8.6683
Max Act: 8.4808. Min Act: -0.1700
Data Index: 444517 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6683. Min Range: -8.6683
Max Act: 8.4183. Min Act: -0.1700
Data Index: 6944146 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6683. Min Range: -8.6683
Max Act: 8.3558. Min Act: -0.1700
Data Index: 7284614 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6683. Min Range: -8.6683
Max Act: 8.3558. Min Act: -0.1700
Data Index: 8382102 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6683. Min Range: -8.6683
Max Act: 8.2308. Min Act: -0.1700
Data Index: 3253425 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6683. Min Range: -8.6683
Max Act: 8.3558. Min Act: -0.1700
Data Index: 2190587 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6683. Min Range: -8.6683
Max Act: 8.2308. Min Act: -0.1700
Data Index: 6557163 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6683. Min Range: -8.6683
Max Act: 8.2933. Min Act: -0.1700
Data Index: 4617200 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6683. Min Range: -8.6683
Max Act: 8.2933. Min Act: -0.1700
Data Index: 1140691 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6683. Min Range: -8.6683
Max Act: 8.1683. Min Act: -0.1700
Data Index: 961236 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6683. Min Range: -8.6683
Max Act: 8.2308. Min Act: -0.1700
Data Index: 7061145 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6683. Min Range: -8.6683
Max Act: 8.2308. Min Act: -0.1700
Data Index: 1139963 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6683. Min Range: -8.6683
Max Act: 8.1683. Min Act: -0.1700
Data Index: 5694413 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6683. Min Range: -8.6683
Max Act: 8.2933. Min Act: -0.1700
Data Index: 2663202 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6683. Min Range: -8.6683
Max Act: 8.1683. Min Act: -0.1700
Data Index: 2149862 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #19