Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2678 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.3367. Min Range: -4.3367
Max Act: 4.3367. Min Act: -0.1700
Data Index: 2809250 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3367. Min Range: -4.3367
Max Act: 4.3367. Min Act: -0.1700
Data Index: 4809077 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3367. Min Range: -4.3367
Max Act: 4.3367. Min Act: -0.1700
Data Index: 6537502 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3367. Min Range: -4.3367
Max Act: 4.3367. Min Act: -0.1700
Data Index: 4624152 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3367. Min Range: -4.3367
Max Act: 4.3367. Min Act: -0.1700
Data Index: 7245226 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3367. Min Range: -4.3367
Max Act: 4.3054. Min Act: -0.1700
Data Index: 3860552 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3367. Min Range: -4.3367
Max Act: 4.3054. Min Act: -0.1700
Data Index: 221356 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3367. Min Range: -4.3367
Max Act: 4.3054. Min Act: -0.1700
Data Index: 7411043 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3367. Min Range: -4.3367
Max Act: 4.2742. Min Act: -0.1700
Data Index: 7281396 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3367. Min Range: -4.3367
Max Act: 4.3054. Min Act: -0.1700
Data Index: 7074334 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3367. Min Range: -4.3367
Max Act: 4.2742. Min Act: -0.1700
Data Index: 4276441 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3367. Min Range: -4.3367
Max Act: 4.2742. Min Act: -0.1700
Data Index: 7151762 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3367. Min Range: -4.3367
Max Act: 4.2742. Min Act: -0.1700
Data Index: 3098705 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3367. Min Range: -4.3367
Max Act: 4.2742. Min Act: -0.1700
Data Index: 7295850 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3367. Min Range: -4.3367
Max Act: 4.2742. Min Act: -0.1700
Data Index: 4236616 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3367. Min Range: -4.3367
Max Act: 4.2742. Min Act: -0.1700
Data Index: 5774386 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3367. Min Range: -4.3367
Max Act: 4.2742. Min Act: -0.1700
Data Index: 5176192 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3367. Min Range: -4.3367
Max Act: 4.2742. Min Act: -0.1700
Data Index: 3915472 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3367. Min Range: -4.3367
Max Act: 4.2742. Min Act: -0.1700
Data Index: 1977816 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3367. Min Range: -4.3367
Max Act: 4.2429. Min Act: -0.1700
Data Index: 3582421 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19