Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 471 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.6113. Min Range: -3.6113
Max Act: 3.6113. Min Act: -0.1700
Data Index: 3670378 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6113. Min Range: -3.6113
Max Act: 3.5800. Min Act: -0.1700
Data Index: 6590444 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6113. Min Range: -3.6113
Max Act: 3.5800. Min Act: -0.1700
Data Index: 6026082 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6113. Min Range: -3.6113
Max Act: 3.5486. Min Act: -0.1700
Data Index: 3362487 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6113. Min Range: -3.6113
Max Act: 3.5800. Min Act: -0.1700
Data Index: 3668870 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6113. Min Range: -3.6113
Max Act: 3.5800. Min Act: -0.1700
Data Index: 1470586 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6113. Min Range: -3.6113
Max Act: 3.5800. Min Act: -0.1700
Data Index: 5653166 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6113. Min Range: -3.6113
Max Act: 3.5486. Min Act: -0.1700
Data Index: 2064718 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6113. Min Range: -3.6113
Max Act: 3.5800. Min Act: -0.1700
Data Index: 4790618 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6113. Min Range: -3.6113
Max Act: 3.5173. Min Act: -0.1700
Data Index: 4510535 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6113. Min Range: -3.6113
Max Act: 3.5486. Min Act: -0.1700
Data Index: 6008309 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6113. Min Range: -3.6113
Max Act: 3.5486. Min Act: -0.1700
Data Index: 5011872 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6113. Min Range: -3.6113
Max Act: 3.5486. Min Act: -0.1700
Data Index: 4792003 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6113. Min Range: -3.6113
Max Act: 3.5486. Min Act: -0.1700
Data Index: 4522585 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6113. Min Range: -3.6113
Max Act: 3.5486. Min Act: -0.1700
Data Index: 2148118 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6113. Min Range: -3.6113
Max Act: 3.5486. Min Act: -0.1700
Data Index: 4283722 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6113. Min Range: -3.6113
Max Act: 3.5486. Min Act: -0.1700
Data Index: 4095820 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6113. Min Range: -3.6113
Max Act: 3.5486. Min Act: -0.1700
Data Index: 1478079 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6113. Min Range: -3.6113
Max Act: 3.5486. Min Act: -0.1700
Data Index: 3523503 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6113. Min Range: -3.6113
Max Act: 3.5486. Min Act: -0.1700
Data Index: 3236024 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19