Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 5069 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 11.0484. Min Range: -11.0484
Max Act: 11.0484. Min Act: -0.1700
Data Index: 5446637 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.0484. Min Range: -11.0484
Max Act: 10.4234. Min Act: -0.1700
Data Index: 5904686 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.0484. Min Range: -11.0484
Max Act: 10.2984. Min Act: -0.1700
Data Index: 6768664 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.0484. Min Range: -11.0484
Max Act: 10.1109. Min Act: -0.1700
Data Index: 8028405 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.0484. Min Range: -11.0484
Max Act: 9.9859. Min Act: -0.1700
Data Index: 5842735 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.0484. Min Range: -11.0484
Max Act: 9.9234. Min Act: -0.1700
Data Index: 4598584 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.0484. Min Range: -11.0484
Max Act: 9.7984. Min Act: -0.1700
Data Index: 1257000 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.0484. Min Range: -11.0484
Max Act: 9.6734. Min Act: -0.1700
Data Index: 2934204 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.0484. Min Range: -11.0484
Max Act: 9.6734. Min Act: -0.1700
Data Index: 4422292 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.0484. Min Range: -11.0484
Max Act: 9.6109. Min Act: -0.1700
Data Index: 5367343 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.0484. Min Range: -11.0484
Max Act: 9.5484. Min Act: -0.1700
Data Index: 4725147 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.0484. Min Range: -11.0484
Max Act: 9.6109. Min Act: -0.1700
Data Index: 4135736 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.0484. Min Range: -11.0484
Max Act: 9.5484. Min Act: -0.1700
Data Index: 6387041 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.0484. Min Range: -11.0484
Max Act: 9.4859. Min Act: -0.1700
Data Index: 1033423 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.0484. Min Range: -11.0484
Max Act: 9.4859. Min Act: -0.1700
Data Index: 8059380 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.0484. Min Range: -11.0484
Max Act: 9.3609. Min Act: -0.1700
Data Index: 2329687 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.0484. Min Range: -11.0484
Max Act: 9.3609. Min Act: -0.1700
Data Index: 7490587 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.0484. Min Range: -11.0484
Max Act: 9.3609. Min Act: -0.1700
Data Index: 7821279 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.0484. Min Range: -11.0484
Max Act: 9.3609. Min Act: -0.1700
Data Index: 2607022 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.0484. Min Range: -11.0484
Max Act: 9.3609. Min Act: -0.1700
Data Index: 5026048 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #19