Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2296 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.3701. Min Range: -3.3701
Max Act: 3.3701. Min Act: -0.1700
Data Index: 4139459 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3701. Min Range: -3.3701
Max Act: 3.3701. Min Act: -0.1700
Data Index: 611355 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3701. Min Range: -3.3701
Max Act: 3.3388. Min Act: -0.1700
Data Index: 3959038 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3701. Min Range: -3.3701
Max Act: 3.3388. Min Act: -0.1700
Data Index: 1829689 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3701. Min Range: -3.3701
Max Act: 3.3388. Min Act: -0.1700
Data Index: 1858252 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3701. Min Range: -3.3701
Max Act: 3.3388. Min Act: -0.1700
Data Index: 5028786 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3701. Min Range: -3.3701
Max Act: 3.3388. Min Act: -0.1700
Data Index: 245412 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3701. Min Range: -3.3701
Max Act: 3.3388. Min Act: -0.1700
Data Index: 5913254 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3701. Min Range: -3.3701
Max Act: 3.3074. Min Act: -0.1700
Data Index: 4887560 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3701. Min Range: -3.3701
Max Act: 3.3074. Min Act: -0.1700
Data Index: 814035 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3701. Min Range: -3.3701
Max Act: 3.3074. Min Act: -0.1700
Data Index: 5997386 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3701. Min Range: -3.3701
Max Act: 3.2760. Min Act: -0.1700
Data Index: 5249413 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3701. Min Range: -3.3701
Max Act: 3.2760. Min Act: -0.1700
Data Index: 8486709 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3701. Min Range: -3.3701
Max Act: 3.2760. Min Act: -0.1700
Data Index: 3406046 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3701. Min Range: -3.3701
Max Act: 3.2446. Min Act: -0.1700
Data Index: 7326959 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3701. Min Range: -3.3701
Max Act: 3.2760. Min Act: -0.1700
Data Index: 6489261 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3701. Min Range: -3.3701
Max Act: 3.2760. Min Act: -0.1700
Data Index: 5319591 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3701. Min Range: -3.3701
Max Act: 3.2760. Min Act: -0.1700
Data Index: 4468323 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3701. Min Range: -3.3701
Max Act: 3.2760. Min Act: -0.1700
Data Index: 1547154 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3701. Min Range: -3.3701
Max Act: 3.2760. Min Act: -0.1700
Data Index: 4002871 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19