Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 5096 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.3122. Min Range: -4.3122
Max Act: 4.3122. Min Act: -0.1700
Data Index: 6615208 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3122. Min Range: -4.3122
Max Act: 4.2809. Min Act: -0.1700
Data Index: 4118506 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3122. Min Range: -4.3122
Max Act: 4.2809. Min Act: -0.1700
Data Index: 7929620 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3122. Min Range: -4.3122
Max Act: 4.2184. Min Act: -0.1700
Data Index: 4765184 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3122. Min Range: -4.3122
Max Act: 4.2184. Min Act: -0.1700
Data Index: 1121156 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3122. Min Range: -4.3122
Max Act: 4.1559. Min Act: -0.1700
Data Index: 6686635 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3122. Min Range: -4.3122
Max Act: 4.1559. Min Act: -0.1700
Data Index: 1446883 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3122. Min Range: -4.3122
Max Act: 4.1247. Min Act: -0.1700
Data Index: 1966530 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3122. Min Range: -4.3122
Max Act: 4.0622. Min Act: -0.1700
Data Index: 394238 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3122. Min Range: -4.3122
Max Act: 4.0934. Min Act: -0.1700
Data Index: 3286696 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3122. Min Range: -4.3122
Max Act: 4.1247. Min Act: -0.1700
Data Index: 4390099 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3122. Min Range: -4.3122
Max Act: 4.0934. Min Act: -0.1700
Data Index: 5003708 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3122. Min Range: -4.3122
Max Act: 4.1247. Min Act: -0.1700
Data Index: 7948837 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3122. Min Range: -4.3122
Max Act: 4.0622. Min Act: -0.1700
Data Index: 585529 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3122. Min Range: -4.3122
Max Act: 4.0309. Min Act: -0.1700
Data Index: 2854589 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3122. Min Range: -4.3122
Max Act: 4.0934. Min Act: -0.1700
Data Index: 5458825 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3122. Min Range: -4.3122
Max Act: 4.0622. Min Act: -0.1700
Data Index: 6462953 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3122. Min Range: -4.3122
Max Act: 4.0622. Min Act: -0.1700
Data Index: 1682321 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3122. Min Range: -4.3122
Max Act: 4.0622. Min Act: -0.1700
Data Index: 1851872 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3122. Min Range: -4.3122
Max Act: 4.0622. Min Act: -0.1700
Data Index: 557737 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #19