Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 744 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0613. Min Range: -6.0613
Max Act: 6.0613. Min Act: -0.1700
Data Index: 7699672 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0613. Min Range: -6.0613
Max Act: 6.0301. Min Act: -0.1700
Data Index: 7065267 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0613. Min Range: -6.0613
Max Act: 5.9988. Min Act: -0.1700
Data Index: 3628922 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0613. Min Range: -6.0613
Max Act: 5.9988. Min Act: -0.1700
Data Index: 3980293 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0613. Min Range: -6.0613
Max Act: 5.9363. Min Act: -0.1700
Data Index: 1748964 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0613. Min Range: -6.0613
Max Act: 5.9051. Min Act: -0.1700
Data Index: 5551045 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0613. Min Range: -6.0613
Max Act: 5.9051. Min Act: -0.1700
Data Index: 457133 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0613. Min Range: -6.0613
Max Act: 5.9051. Min Act: -0.1700
Data Index: 2174625 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0613. Min Range: -6.0613
Max Act: 5.9363. Min Act: -0.1700
Data Index: 5354587 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0613. Min Range: -6.0613
Max Act: 5.8738. Min Act: -0.1700
Data Index: 4885703 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0613. Min Range: -6.0613
Max Act: 5.8738. Min Act: -0.1700
Data Index: 1983541 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0613. Min Range: -6.0613
Max Act: 5.8426. Min Act: -0.1700
Data Index: 2121106 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0613. Min Range: -6.0613
Max Act: 5.8113. Min Act: -0.1700
Data Index: 1870835 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0613. Min Range: -6.0613
Max Act: 5.8113. Min Act: -0.1700
Data Index: 8063061 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0613. Min Range: -6.0613
Max Act: 5.8113. Min Act: -0.1700
Data Index: 2723872 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0613. Min Range: -6.0613
Max Act: 5.8113. Min Act: -0.1700
Data Index: 2946888 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0613. Min Range: -6.0613
Max Act: 5.7801. Min Act: -0.1700
Data Index: 1483089 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0613. Min Range: -6.0613
Max Act: 5.8113. Min Act: -0.1700
Data Index: 1751253 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0613. Min Range: -6.0613
Max Act: 5.8113. Min Act: -0.1700
Data Index: 7290844 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0613. Min Range: -6.0613
Max Act: 5.8113. Min Act: -0.1700
Data Index: 2071820 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #19