Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3721 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.5109. Min Range: -3.5109
Max Act: 3.5109. Min Act: -0.1700
Data Index: 5248480 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5109. Min Range: -3.5109
Max Act: 3.4952. Min Act: -0.1700
Data Index: 1232972 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5109. Min Range: -3.5109
Max Act: 3.4796. Min Act: -0.1700
Data Index: 2864823 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5109. Min Range: -3.5109
Max Act: 3.4639. Min Act: -0.1700
Data Index: 1060024 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5109. Min Range: -3.5109
Max Act: 3.4639. Min Act: -0.1700
Data Index: 5195358 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5109. Min Range: -3.5109
Max Act: 3.4169. Min Act: -0.1700
Data Index: 4772527 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5109. Min Range: -3.5109
Max Act: 3.4326. Min Act: -0.1700
Data Index: 6576921 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5109. Min Range: -3.5109
Max Act: 3.4326. Min Act: -0.1700
Data Index: 8411760 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5109. Min Range: -3.5109
Max Act: 3.4169. Min Act: -0.1700
Data Index: 6438199 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5109. Min Range: -3.5109
Max Act: 3.4326. Min Act: -0.1700
Data Index: 4472183 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5109. Min Range: -3.5109
Max Act: 3.3855. Min Act: -0.1700
Data Index: 4913603 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5109. Min Range: -3.5109
Max Act: 3.4012. Min Act: -0.1700
Data Index: 7600994 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5109. Min Range: -3.5109
Max Act: 3.4012. Min Act: -0.1700
Data Index: 4496385 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5109. Min Range: -3.5109
Max Act: 3.4012. Min Act: -0.1700
Data Index: 8481683 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5109. Min Range: -3.5109
Max Act: 3.4012. Min Act: -0.1700
Data Index: 7032677 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5109. Min Range: -3.5109
Max Act: 3.4012. Min Act: -0.1700
Data Index: 6994436 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5109. Min Range: -3.5109
Max Act: 3.4012. Min Act: -0.1700
Data Index: 5491616 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5109. Min Range: -3.5109
Max Act: 3.4012. Min Act: -0.1700
Data Index: 2008129 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5109. Min Range: -3.5109
Max Act: 3.4012. Min Act: -0.1700
Data Index: 85269 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5109. Min Range: -3.5109
Max Act: 3.3855. Min Act: -0.1700
Data Index: 2476122 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #19