Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 303 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 0.4865. Min Range: -0.4865
Max Act: 0.4865. Min Act: -0.1700
Data Index: 7624082 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.4865. Min Range: -0.4865
Max Act: 0.4570. Min Act: -0.1697
Data Index: 3444623 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.4865. Min Range: -0.4865
Max Act: 0.4570. Min Act: -0.1700
Data Index: 7873226 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.4865. Min Range: -0.4865
Max Act: 0.4424. Min Act: -0.1700
Data Index: 820935 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.4865. Min Range: -0.4865
Max Act: 0.4424. Min Act: -0.1697
Data Index: 5848185 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.4865. Min Range: -0.4865
Max Act: 0.4351. Min Act: -0.1700
Data Index: 1749303 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.4865. Min Range: -0.4865
Max Act: 0.4065. Min Act: -0.1700
Data Index: 10554 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.4865. Min Range: -0.4865
Max Act: 0.3994. Min Act: -0.1700
Data Index: 2109608 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.4865. Min Range: -0.4865
Max Act: 0.3994. Min Act: -0.1700
Data Index: 7639534 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.4865. Min Range: -0.4865
Max Act: 0.3854. Min Act: -0.1700
Data Index: 6577424 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.4865. Min Range: -0.4865
Max Act: 0.3784. Min Act: -0.1700
Data Index: 5195642 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.4865. Min Range: -0.4865
Max Act: 0.3784. Min Act: -0.1700
Data Index: 731178 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.4865. Min Range: -0.4865
Max Act: 0.3646. Min Act: -0.1700
Data Index: 7337159 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.4865. Min Range: -0.4865
Max Act: 0.3715. Min Act: -0.1700
Data Index: 8487591 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.4865. Min Range: -0.4865
Max Act: 0.3646. Min Act: -0.1697
Data Index: 874949 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.4865. Min Range: -0.4865
Max Act: 0.3646. Min Act: -0.1700
Data Index: 7130181 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.4865. Min Range: -0.4865
Max Act: 0.3646. Min Act: -0.1698
Data Index: 2708824 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.4865. Min Range: -0.4865
Max Act: 0.3646. Min Act: -0.1700
Data Index: 8424086 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.4865. Min Range: -0.4865
Max Act: 0.3646. Min Act: -0.1700
Data Index: 5548063 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.4865. Min Range: -0.4865
Max Act: 0.3509. Min Act: -0.1700
Data Index: 4496724 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #19