Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4059 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.3372. Min Range: -6.3372
Max Act: 6.3372. Min Act: -0.1700
Data Index: 5501042 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3372. Min Range: -6.3372
Max Act: 6.3372. Min Act: -0.1700
Data Index: 6617952 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3372. Min Range: -6.3372
Max Act: 6.2122. Min Act: -0.1700
Data Index: 7229465 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3372. Min Range: -6.3372
Max Act: 6.1809. Min Act: -0.1700
Data Index: 5839688 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3372. Min Range: -6.3372
Max Act: 6.1184. Min Act: -0.1700
Data Index: 4494981 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3372. Min Range: -6.3372
Max Act: 6.1184. Min Act: -0.1700
Data Index: 3274090 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3372. Min Range: -6.3372
Max Act: 6.0559. Min Act: -0.1700
Data Index: 1658526 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3372. Min Range: -6.3372
Max Act: 6.0559. Min Act: -0.1700
Data Index: 4045939 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3372. Min Range: -6.3372
Max Act: 5.9934. Min Act: -0.1700
Data Index: 4857832 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3372. Min Range: -6.3372
Max Act: 5.9622. Min Act: -0.1700
Data Index: 582143 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3372. Min Range: -6.3372
Max Act: 5.8684. Min Act: -0.1700
Data Index: 4175977 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3372. Min Range: -6.3372
Max Act: 5.8997. Min Act: -0.1700
Data Index: 4836819 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3372. Min Range: -6.3372
Max Act: 5.8997. Min Act: -0.1700
Data Index: 7269602 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3372. Min Range: -6.3372
Max Act: 5.8684. Min Act: -0.1700
Data Index: 8619107 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3372. Min Range: -6.3372
Max Act: 5.8684. Min Act: -0.1700
Data Index: 7938276 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3372. Min Range: -6.3372
Max Act: 5.8059. Min Act: -0.1700
Data Index: 6085244 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3372. Min Range: -6.3372
Max Act: 5.8372. Min Act: -0.1700
Data Index: 786612 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3372. Min Range: -6.3372
Max Act: 5.7747. Min Act: -0.1700
Data Index: 2826911 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3372. Min Range: -6.3372
Max Act: 5.8372. Min Act: -0.1700
Data Index: 1801909 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3372. Min Range: -6.3372
Max Act: 5.8059. Min Act: -0.1700
Data Index: 6858408 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #19