Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1356 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7223. Min Range: -4.7223
Max Act: 4.7223. Min Act: -0.1700
Data Index: 2577390 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7223. Min Range: -4.7223
Max Act: 4.7223. Min Act: -0.1700
Data Index: 6681806 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7223. Min Range: -4.7223
Max Act: 4.6911. Min Act: -0.1700
Data Index: 437880 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7223. Min Range: -4.7223
Max Act: 4.5661. Min Act: -0.1700
Data Index: 4038086 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7223. Min Range: -4.7223
Max Act: 4.5661. Min Act: -0.1700
Data Index: 101844 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7223. Min Range: -4.7223
Max Act: 4.5973. Min Act: -0.1700
Data Index: 8729621 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7223. Min Range: -4.7223
Max Act: 4.5348. Min Act: -0.1700
Data Index: 1106888 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7223. Min Range: -4.7223
Max Act: 4.5348. Min Act: -0.1700
Data Index: 4651308 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7223. Min Range: -4.7223
Max Act: 4.4723. Min Act: -0.1700
Data Index: 2387900 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7223. Min Range: -4.7223
Max Act: 4.4723. Min Act: -0.1700
Data Index: 8581956 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7223. Min Range: -4.7223
Max Act: 4.5036. Min Act: -0.1700
Data Index: 6813742 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7223. Min Range: -4.7223
Max Act: 4.4723. Min Act: -0.1700
Data Index: 4228269 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7223. Min Range: -4.7223
Max Act: 4.4411. Min Act: -0.1700
Data Index: 2152252 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7223. Min Range: -4.7223
Max Act: 4.4723. Min Act: -0.1700
Data Index: 7415823 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7223. Min Range: -4.7223
Max Act: 4.4411. Min Act: -0.1700
Data Index: 257155 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7223. Min Range: -4.7223
Max Act: 4.4411. Min Act: -0.1700
Data Index: 2921647 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7223. Min Range: -4.7223
Max Act: 4.4098. Min Act: -0.1700
Data Index: 8434869 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7223. Min Range: -4.7223
Max Act: 4.3786. Min Act: -0.1700
Data Index: 7125771 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7223. Min Range: -4.7223
Max Act: 4.3786. Min Act: -0.1700
Data Index: 4164003 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7223. Min Range: -4.7223
Max Act: 4.3786. Min Act: -0.1700
Data Index: 2794549 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #19