Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3362 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.5356. Min Range: -4.5356
Max Act: 4.5356. Min Act: -0.1700
Data Index: 3824265 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5356. Min Range: -4.5356
Max Act: 4.5356. Min Act: -0.1700
Data Index: 8032773 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5356. Min Range: -4.5356
Max Act: 4.5043. Min Act: -0.1700
Data Index: 3184727 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5356. Min Range: -4.5356
Max Act: 4.5043. Min Act: -0.1700
Data Index: 90283 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5356. Min Range: -4.5356
Max Act: 4.4731. Min Act: -0.1700
Data Index: 5043319 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5356. Min Range: -4.5356
Max Act: 4.4418. Min Act: -0.1700
Data Index: 3634821 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5356. Min Range: -4.5356
Max Act: 4.4418. Min Act: -0.1700
Data Index: 8801789 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5356. Min Range: -4.5356
Max Act: 4.4418. Min Act: -0.1700
Data Index: 214198 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5356. Min Range: -4.5356
Max Act: 4.4418. Min Act: -0.1700
Data Index: 6886817 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5356. Min Range: -4.5356
Max Act: 4.4418. Min Act: -0.1700
Data Index: 4650242 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5356. Min Range: -4.5356
Max Act: 4.4418. Min Act: -0.1700
Data Index: 4562231 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5356. Min Range: -4.5356
Max Act: 4.4106. Min Act: -0.1700
Data Index: 1660752 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5356. Min Range: -4.5356
Max Act: 4.4106. Min Act: -0.1700
Data Index: 2988577 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5356. Min Range: -4.5356
Max Act: 4.4106. Min Act: -0.1700
Data Index: 2457283 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5356. Min Range: -4.5356
Max Act: 4.4106. Min Act: -0.1699
Data Index: 833278 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5356. Min Range: -4.5356
Max Act: 4.4106. Min Act: -0.1700
Data Index: 5143896 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5356. Min Range: -4.5356
Max Act: 4.4106. Min Act: -0.1700
Data Index: 6987908 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5356. Min Range: -4.5356
Max Act: 4.4106. Min Act: -0.1700
Data Index: 4523007 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5356. Min Range: -4.5356
Max Act: 4.4106. Min Act: -0.1700
Data Index: 2462265 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5356. Min Range: -4.5356
Max Act: 4.4106. Min Act: -0.1700
Data Index: 3233935 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19