Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2809 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.1545. Min Range: -3.1545
Max Act: 3.1230. Min Act: -0.1700
Data Index: 2563734 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1545. Min Range: -3.1545
Max Act: 3.1545. Min Act: -0.1700
Data Index: 4880792 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1545. Min Range: -3.1545
Max Act: 3.0915. Min Act: -0.1700
Data Index: 6217709 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1545. Min Range: -3.1545
Max Act: 3.0442. Min Act: -0.1700
Data Index: 2825111 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1545. Min Range: -3.1545
Max Act: 3.0284. Min Act: -0.1700
Data Index: 3077264 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1545. Min Range: -3.1545
Max Act: 2.9968. Min Act: -0.1700
Data Index: 5702467 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1545. Min Range: -3.1545
Max Act: 2.9652. Min Act: -0.1700
Data Index: 8019442 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1545. Min Range: -3.1545
Max Act: 2.9493. Min Act: -0.1700
Data Index: 3521627 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1545. Min Range: -3.1545
Max Act: 2.9177. Min Act: -0.1700
Data Index: 2674939 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1545. Min Range: -3.1545
Max Act: 2.9335. Min Act: -0.1700
Data Index: 1923243 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1545. Min Range: -3.1545
Max Act: 2.9018. Min Act: -0.1700
Data Index: 2005571 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1545. Min Range: -3.1545
Max Act: 2.8860. Min Act: -0.1700
Data Index: 616141 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1545. Min Range: -3.1545
Max Act: 2.9018. Min Act: -0.1700
Data Index: 6642762 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1545. Min Range: -3.1545
Max Act: 2.8860. Min Act: -0.1700
Data Index: 5653730 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1545. Min Range: -3.1545
Max Act: 2.8860. Min Act: -0.1700
Data Index: 4604591 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1545. Min Range: -3.1545
Max Act: 2.8701. Min Act: -0.1700
Data Index: 2557525 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1545. Min Range: -3.1545
Max Act: 2.8701. Min Act: -0.1700
Data Index: 3704382 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1545. Min Range: -3.1545
Max Act: 2.8701. Min Act: -0.1700
Data Index: 3077265 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1545. Min Range: -3.1545
Max Act: 2.8542. Min Act: -0.1700
Data Index: 1609422 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1545. Min Range: -3.1545
Max Act: 2.8542. Min Act: -0.1700
Data Index: 616156 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #19