Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3830 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 1.7598. Min Range: -1.7598
Max Act: 1.7598. Min Act: -0.1700
Data Index: 7700762 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.7598. Min Range: -1.7598
Max Act: 1.7425. Min Act: -0.1700
Data Index: 1964446 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.7598. Min Range: -1.7598
Max Act: 1.7425. Min Act: -0.1700
Data Index: 7769605 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.7598. Min Range: -1.7598
Max Act: 1.7252. Min Act: -0.1700
Data Index: 6205636 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.7598. Min Range: -1.7598
Max Act: 1.7252. Min Act: -0.1700
Data Index: 6355532 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.7598. Min Range: -1.7598
Max Act: 1.7252. Min Act: -0.1700
Data Index: 6180259 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.7598. Min Range: -1.7598
Max Act: 1.7252. Min Act: -0.1700
Data Index: 5648512 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.7598. Min Range: -1.7598
Max Act: 1.7079. Min Act: -0.1700
Data Index: 5116068 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.7598. Min Range: -1.7598
Max Act: 1.7252. Min Act: -0.1700
Data Index: 4233771 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.7598. Min Range: -1.7598
Max Act: 1.7252. Min Act: -0.1700
Data Index: 3922305 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.7598. Min Range: -1.7598
Max Act: 1.7252. Min Act: -0.1700
Data Index: 3484701 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.7598. Min Range: -1.7598
Max Act: 1.7252. Min Act: -0.1700
Data Index: 3046076 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.7598. Min Range: -1.7598
Max Act: 1.7252. Min Act: -0.1700
Data Index: 2419887 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.7598. Min Range: -1.7598
Max Act: 1.7252. Min Act: -0.1700
Data Index: 7627411 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.7598. Min Range: -1.7598
Max Act: 1.7079. Min Act: -0.1700
Data Index: 4043119 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.7598. Min Range: -1.7598
Max Act: 1.6905. Min Act: -0.1700
Data Index: 4254996 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.7598. Min Range: -1.7598
Max Act: 1.7079. Min Act: -0.1700
Data Index: 4956904 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.7598. Min Range: -1.7598
Max Act: 1.7079. Min Act: -0.1700
Data Index: 87917 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.7598. Min Range: -1.7598
Max Act: 1.7079. Min Act: -0.1700
Data Index: 475183 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.7598. Min Range: -1.7598
Max Act: 1.7079. Min Act: -0.1700
Data Index: 5578886 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #19