Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2709 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.8928. Min Range: -3.8928
Max Act: 3.8928. Min Act: -0.1700
Data Index: 3577455 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8928. Min Range: -3.8928
Max Act: 3.7677. Min Act: -0.1700
Data Index: 393257 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8928. Min Range: -3.8928
Max Act: 3.7364. Min Act: -0.1700
Data Index: 4478757 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8928. Min Range: -3.8928
Max Act: 3.6739. Min Act: -0.1700
Data Index: 4231935 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8928. Min Range: -3.8928
Max Act: 3.6739. Min Act: -0.1700
Data Index: 6075774 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8928. Min Range: -3.8928
Max Act: 3.6426. Min Act: -0.1700
Data Index: 2999257 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8928. Min Range: -3.8928
Max Act: 3.6426. Min Act: -0.1700
Data Index: 8662475 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8928. Min Range: -3.8928
Max Act: 3.6426. Min Act: -0.1700
Data Index: 8820638 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8928. Min Range: -3.8928
Max Act: 3.6426. Min Act: -0.1700
Data Index: 4355532 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8928. Min Range: -3.8928
Max Act: 3.6426. Min Act: -0.1700
Data Index: 6523857 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8928. Min Range: -3.8928
Max Act: 3.6113. Min Act: -0.1700
Data Index: 517468 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8928. Min Range: -3.8928
Max Act: 3.6113. Min Act: -0.1700
Data Index: 8534067 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8928. Min Range: -3.8928
Max Act: 3.5800. Min Act: -0.1700
Data Index: 5348419 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8928. Min Range: -3.8928
Max Act: 3.5800. Min Act: -0.1700
Data Index: 2973496 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8928. Min Range: -3.8928
Max Act: 3.5487. Min Act: -0.1700
Data Index: 5071568 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8928. Min Range: -3.8928
Max Act: 3.5800. Min Act: -0.1700
Data Index: 6129319 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8928. Min Range: -3.8928
Max Act: 3.5800. Min Act: -0.1700
Data Index: 3166894 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8928. Min Range: -3.8928
Max Act: 3.5173. Min Act: -0.1700
Data Index: 5672645 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8928. Min Range: -3.8928
Max Act: 3.5487. Min Act: -0.1700
Data Index: 5769814 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8928. Min Range: -3.8928
Max Act: 3.5487. Min Act: -0.1700
Data Index: 7249919 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #19