Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3225 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.8932. Min Range: -3.8932
Max Act: 3.8932. Min Act: -0.1700
Data Index: 5140113 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8932. Min Range: -3.8932
Max Act: 3.7056. Min Act: -0.1700
Data Index: 5697113 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8932. Min Range: -3.8932
Max Act: 3.7056. Min Act: -0.1700
Data Index: 4931600 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8932. Min Range: -3.8932
Max Act: 3.6743. Min Act: -0.1700
Data Index: 7556529 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8932. Min Range: -3.8932
Max Act: 3.6743. Min Act: -0.1700
Data Index: 2370007 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8932. Min Range: -3.8932
Max Act: 3.6743. Min Act: -0.1700
Data Index: 158270 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8932. Min Range: -3.8932
Max Act: 3.6743. Min Act: -0.1700
Data Index: 492531 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8932. Min Range: -3.8932
Max Act: 3.6743. Min Act: -0.1700
Data Index: 4911524 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8932. Min Range: -3.8932
Max Act: 3.6743. Min Act: -0.1700
Data Index: 4940835 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8932. Min Range: -3.8932
Max Act: 3.6430. Min Act: -0.1700
Data Index: 3858716 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8932. Min Range: -3.8932
Max Act: 3.6117. Min Act: -0.1700
Data Index: 2108843 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8932. Min Range: -3.8932
Max Act: 3.6430. Min Act: -0.1700
Data Index: 8179791 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8932. Min Range: -3.8932
Max Act: 3.6117. Min Act: -0.1700
Data Index: 7898953 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8932. Min Range: -3.8932
Max Act: 3.6743. Min Act: -0.1700
Data Index: 5957669 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8932. Min Range: -3.8932
Max Act: 3.6117. Min Act: -0.1700
Data Index: 5860681 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8932. Min Range: -3.8932
Max Act: 3.6117. Min Act: -0.1700
Data Index: 767755 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8932. Min Range: -3.8932
Max Act: 3.6117. Min Act: -0.1700
Data Index: 2020790 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8932. Min Range: -3.8932
Max Act: 3.6117. Min Act: -0.1700
Data Index: 8058983 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8932. Min Range: -3.8932
Max Act: 3.6117. Min Act: -0.1700
Data Index: 5602169 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8932. Min Range: -3.8932
Max Act: 3.6117. Min Act: -0.1700
Data Index: 7791503 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #19