Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2138 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7586. Min Range: -6.7586
Max Act: 6.7586. Min Act: -0.1700
Data Index: 4086561 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7586. Min Range: -6.7586
Max Act: 6.0711. Min Act: -0.1700
Data Index: 144239 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7586. Min Range: -6.7586
Max Act: 6.0398. Min Act: -0.1700
Data Index: 8605018 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7586. Min Range: -6.7586
Max Act: 6.0398. Min Act: -0.1700
Data Index: 5991587 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7586. Min Range: -6.7586
Max Act: 6.0086. Min Act: -0.1700
Data Index: 1201922 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7586. Min Range: -6.7586
Max Act: 5.9461. Min Act: -0.1700
Data Index: 2319306 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7586. Min Range: -6.7586
Max Act: 5.9148. Min Act: -0.1700
Data Index: 2141607 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7586. Min Range: -6.7586
Max Act: 5.9148. Min Act: -0.1700
Data Index: 8682971 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7586. Min Range: -6.7586
Max Act: 5.8836. Min Act: -0.1700
Data Index: 1761915 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7586. Min Range: -6.7586
Max Act: 5.8836. Min Act: -0.1700
Data Index: 6278592 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7586. Min Range: -6.7586
Max Act: 5.8836. Min Act: -0.1700
Data Index: 2468102 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7586. Min Range: -6.7586
Max Act: 5.8836. Min Act: -0.1700
Data Index: 6371429 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7586. Min Range: -6.7586
Max Act: 5.8523. Min Act: -0.1700
Data Index: 2018061 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7586. Min Range: -6.7586
Max Act: 5.8523. Min Act: -0.1700
Data Index: 3701050 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7586. Min Range: -6.7586
Max Act: 5.8523. Min Act: -0.1700
Data Index: 6906099 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7586. Min Range: -6.7586
Max Act: 5.8523. Min Act: -0.1700
Data Index: 2535864 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7586. Min Range: -6.7586
Max Act: 5.8211. Min Act: -0.1700
Data Index: 4160180 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7586. Min Range: -6.7586
Max Act: 5.8211. Min Act: -0.1700
Data Index: 2391451 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7586. Min Range: -6.7586
Max Act: 5.8523. Min Act: -0.1700
Data Index: 2173893 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7586. Min Range: -6.7586
Max Act: 5.7898. Min Act: -0.1700
Data Index: 3767232 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #19