Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4182 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3044. Min Range: -5.3044
Max Act: 5.3044. Min Act: -0.1700
Data Index: 671634 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3044. Min Range: -5.3044
Max Act: 5.0231. Min Act: -0.1700
Data Index: 4502634 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3044. Min Range: -5.3044
Max Act: 4.9606. Min Act: -0.1700
Data Index: 1071996 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3044. Min Range: -5.3044
Max Act: 4.8669. Min Act: -0.1700
Data Index: 2451535 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3044. Min Range: -5.3044
Max Act: 4.8669. Min Act: -0.1700
Data Index: 184742 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3044. Min Range: -5.3044
Max Act: 4.8356. Min Act: -0.1700
Data Index: 3712029 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3044. Min Range: -5.3044
Max Act: 4.8044. Min Act: -0.1700
Data Index: 7264853 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3044. Min Range: -5.3044
Max Act: 4.8044. Min Act: -0.1700
Data Index: 5989023 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3044. Min Range: -5.3044
Max Act: 4.7419. Min Act: -0.1700
Data Index: 4930605 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3044. Min Range: -5.3044
Max Act: 4.7106. Min Act: -0.1700
Data Index: 6992709 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3044. Min Range: -5.3044
Max Act: 4.7106. Min Act: -0.1700
Data Index: 2940437 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3044. Min Range: -5.3044
Max Act: 4.7106. Min Act: -0.1700
Data Index: 6953539 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3044. Min Range: -5.3044
Max Act: 4.6794. Min Act: -0.1700
Data Index: 5789534 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3044. Min Range: -5.3044
Max Act: 4.6794. Min Act: -0.1700
Data Index: 8439647 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3044. Min Range: -5.3044
Max Act: 4.6481. Min Act: -0.1700
Data Index: 1427571 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3044. Min Range: -5.3044
Max Act: 4.6481. Min Act: -0.1700
Data Index: 6732820 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3044. Min Range: -5.3044
Max Act: 4.6481. Min Act: -0.1700
Data Index: 3160008 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3044. Min Range: -5.3044
Max Act: 4.6169. Min Act: -0.1700
Data Index: 3928870 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3044. Min Range: -5.3044
Max Act: 4.6169. Min Act: -0.1700
Data Index: 7059904 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3044. Min Range: -5.3044
Max Act: 4.5856. Min Act: -0.1700
Data Index: 1376785 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #19