Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5890 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4002. Min Range: -5.4002
Max Act: 5.4002. Min Act: -0.1700
Data Index: 3317419 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4002. Min Range: -5.4002
Max Act: 5.3690. Min Act: -0.1700
Data Index: 2224982 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4002. Min Range: -5.4002
Max Act: 5.4002. Min Act: -0.1700
Data Index: 6515916 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4002. Min Range: -5.4002
Max Act: 5.3690. Min Act: -0.1700
Data Index: 7240937 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4002. Min Range: -5.4002
Max Act: 5.3377. Min Act: -0.1700
Data Index: 8131601 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4002. Min Range: -5.4002
Max Act: 5.3377. Min Act: -0.1700
Data Index: 1798620 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4002. Min Range: -5.4002
Max Act: 5.3377. Min Act: -0.1700
Data Index: 7662803 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4002. Min Range: -5.4002
Max Act: 5.3377. Min Act: -0.1700
Data Index: 6890579 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4002. Min Range: -5.4002
Max Act: 5.3377. Min Act: -0.1700
Data Index: 1271765 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4002. Min Range: -5.4002
Max Act: 5.3377. Min Act: -0.1700
Data Index: 84117 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4002. Min Range: -5.4002
Max Act: 5.3377. Min Act: -0.1700
Data Index: 7316940 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4002. Min Range: -5.4002
Max Act: 5.3065. Min Act: -0.1700
Data Index: 4790062 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4002. Min Range: -5.4002
Max Act: 5.3065. Min Act: -0.1700
Data Index: 1879107 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4002. Min Range: -5.4002
Max Act: 5.3065. Min Act: -0.1700
Data Index: 8533777 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4002. Min Range: -5.4002
Max Act: 5.3065. Min Act: -0.1700
Data Index: 5244097 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4002. Min Range: -5.4002
Max Act: 5.3065. Min Act: -0.1700
Data Index: 76356 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4002. Min Range: -5.4002
Max Act: 5.2752. Min Act: -0.1700
Data Index: 8075656 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4002. Min Range: -5.4002
Max Act: 5.2752. Min Act: -0.1700
Data Index: 3251589 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4002. Min Range: -5.4002
Max Act: 5.2752. Min Act: -0.1700
Data Index: 6384634 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4002. Min Range: -5.4002
Max Act: 5.2752. Min Act: -0.1700
Data Index: 25548 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #19