Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2454 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9123. Min Range: -3.9123
Max Act: 3.9123. Min Act: -0.1700
Data Index: 3712714 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9123. Min Range: -3.9123
Max Act: 3.7872. Min Act: -0.1700
Data Index: 3021587 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9123. Min Range: -3.9123
Max Act: 3.7247. Min Act: -0.1700
Data Index: 3286601 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9123. Min Range: -3.9123
Max Act: 3.7247. Min Act: -0.1700
Data Index: 8611163 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9123. Min Range: -3.9123
Max Act: 3.7247. Min Act: -0.1700
Data Index: 5489119 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9123. Min Range: -3.9123
Max Act: 3.7247. Min Act: -0.1700
Data Index: 7998806 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9123. Min Range: -3.9123
Max Act: 3.7247. Min Act: -0.1700
Data Index: 6669991 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9123. Min Range: -3.9123
Max Act: 3.6934. Min Act: -0.1700
Data Index: 396420 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9123. Min Range: -3.9123
Max Act: 3.6934. Min Act: -0.1700
Data Index: 8800679 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9123. Min Range: -3.9123
Max Act: 3.6934. Min Act: -0.1700
Data Index: 538105 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9123. Min Range: -3.9123
Max Act: 3.6934. Min Act: -0.1700
Data Index: 4058968 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9123. Min Range: -3.9123
Max Act: 3.6934. Min Act: -0.1700
Data Index: 8232238 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9123. Min Range: -3.9123
Max Act: 3.6934. Min Act: -0.1700
Data Index: 101301 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9123. Min Range: -3.9123
Max Act: 3.6934. Min Act: -0.1700
Data Index: 6569821 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9123. Min Range: -3.9123
Max Act: 3.6934. Min Act: -0.1700
Data Index: 1412094 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9123. Min Range: -3.9123
Max Act: 3.6934. Min Act: -0.1700
Data Index: 6256000 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9123. Min Range: -3.9123
Max Act: 3.6934. Min Act: -0.1700
Data Index: 3121915 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9123. Min Range: -3.9123
Max Act: 3.6934. Min Act: -0.1700
Data Index: 4816935 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9123. Min Range: -3.9123
Max Act: 3.6934. Min Act: -0.1700
Data Index: 3004238 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9123. Min Range: -3.9123
Max Act: 3.6934. Min Act: -0.1700
Data Index: 4305647 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19