Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 897 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6624. Min Range: -6.6624
Max Act: 6.6624. Min Act: -0.1700
Data Index: 8739112 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6624. Min Range: -6.6624
Max Act: 6.6312. Min Act: -0.1700
Data Index: 5652789 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6624. Min Range: -6.6624
Max Act: 6.5687. Min Act: -0.1700
Data Index: 7398413 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6624. Min Range: -6.6624
Max Act: 6.4749. Min Act: -0.1700
Data Index: 1292591 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6624. Min Range: -6.6624
Max Act: 6.4124. Min Act: -0.1700
Data Index: 6984744 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6624. Min Range: -6.6624
Max Act: 6.3499. Min Act: -0.1700
Data Index: 8040795 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6624. Min Range: -6.6624
Max Act: 6.3499. Min Act: -0.1700
Data Index: 1329283 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6624. Min Range: -6.6624
Max Act: 6.2874. Min Act: -0.1700
Data Index: 3429790 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6624. Min Range: -6.6624
Max Act: 6.2874. Min Act: -0.1700
Data Index: 2315669 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6624. Min Range: -6.6624
Max Act: 6.2562. Min Act: -0.1700
Data Index: 4306400 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6624. Min Range: -6.6624
Max Act: 6.2874. Min Act: -0.1700
Data Index: 2897311 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6624. Min Range: -6.6624
Max Act: 6.2562. Min Act: -0.1700
Data Index: 606818 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6624. Min Range: -6.6624
Max Act: 6.2249. Min Act: -0.1700
Data Index: 229498 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6624. Min Range: -6.6624
Max Act: 6.2249. Min Act: -0.1700
Data Index: 5669106 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6624. Min Range: -6.6624
Max Act: 6.1937. Min Act: -0.1700
Data Index: 7904659 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6624. Min Range: -6.6624
Max Act: 6.1937. Min Act: -0.1700
Data Index: 6219478 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6624. Min Range: -6.6624
Max Act: 6.1937. Min Act: -0.1700
Data Index: 5502137 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6624. Min Range: -6.6624
Max Act: 6.1624. Min Act: -0.1700
Data Index: 1822223 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6624. Min Range: -6.6624
Max Act: 6.1624. Min Act: -0.1700
Data Index: 6093886 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6624. Min Range: -6.6624
Max Act: 6.1937. Min Act: -0.1700
Data Index: 5534994 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #19