Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3021 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.2980. Min Range: -5.2980
Max Act: 5.2980. Min Act: -0.1700
Data Index: 4831831 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2980. Min Range: -5.2980
Max Act: 5.2980. Min Act: -0.1700
Data Index: 4831840 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2980. Min Range: -5.2980
Max Act: 5.2980. Min Act: -0.1700
Data Index: 2776439 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2980. Min Range: -5.2980
Max Act: 5.2355. Min Act: -0.1700
Data Index: 498420 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2980. Min Range: -5.2980
Max Act: 5.1418. Min Act: -0.1700
Data Index: 1178140 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2980. Min Range: -5.2980
Max Act: 5.1105. Min Act: -0.1700
Data Index: 8271752 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2980. Min Range: -5.2980
Max Act: 5.0793. Min Act: -0.1700
Data Index: 6658478 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2980. Min Range: -5.2980
Max Act: 5.0793. Min Act: -0.1700
Data Index: 216457 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2980. Min Range: -5.2980
Max Act: 5.0168. Min Act: -0.1700
Data Index: 1408950 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2980. Min Range: -5.2980
Max Act: 5.0480. Min Act: -0.1700
Data Index: 5695161 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2980. Min Range: -5.2980
Max Act: 5.0793. Min Act: -0.1700
Data Index: 7998382 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2980. Min Range: -5.2980
Max Act: 5.0168. Min Act: -0.1700
Data Index: 8717984 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2980. Min Range: -5.2980
Max Act: 5.0168. Min Act: -0.1700
Data Index: 4399024 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2980. Min Range: -5.2980
Max Act: 4.9855. Min Act: -0.1700
Data Index: 2734228 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2980. Min Range: -5.2980
Max Act: 5.0168. Min Act: -0.1700
Data Index: 2418178 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2980. Min Range: -5.2980
Max Act: 5.0168. Min Act: -0.1700
Data Index: 7295551 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2980. Min Range: -5.2980
Max Act: 5.0480. Min Act: -0.1700
Data Index: 2074379 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2980. Min Range: -5.2980
Max Act: 5.0168. Min Act: -0.1700
Data Index: 6439985 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2980. Min Range: -5.2980
Max Act: 5.0168. Min Act: -0.1700
Data Index: 5625864 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2980. Min Range: -5.2980
Max Act: 5.0168. Min Act: -0.1700
Data Index: 4520762 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #19