Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1482 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2975. Min Range: -7.2975
Max Act: 7.2975. Min Act: -0.1700
Data Index: 5155428 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2975. Min Range: -7.2975
Max Act: 7.1100. Min Act: -0.1700
Data Index: 8330258 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2975. Min Range: -7.2975
Max Act: 7.0475. Min Act: -0.1700
Data Index: 6686944 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2975. Min Range: -7.2975
Max Act: 7.0162. Min Act: -0.1700
Data Index: 2823276 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2975. Min Range: -7.2975
Max Act: 6.8912. Min Act: -0.1700
Data Index: 1515644 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2975. Min Range: -7.2975
Max Act: 6.8600. Min Act: -0.1700
Data Index: 3160035 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2975. Min Range: -7.2975
Max Act: 6.9225. Min Act: -0.1700
Data Index: 2653277 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2975. Min Range: -7.2975
Max Act: 6.8600. Min Act: -0.1700
Data Index: 3390053 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2975. Min Range: -7.2975
Max Act: 6.8287. Min Act: -0.1700
Data Index: 213033 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2975. Min Range: -7.2975
Max Act: 6.8287. Min Act: -0.1700
Data Index: 2714815 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2975. Min Range: -7.2975
Max Act: 6.8287. Min Act: -0.1700
Data Index: 1845184 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2975. Min Range: -7.2975
Max Act: 6.7975. Min Act: -0.1700
Data Index: 7998557 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2975. Min Range: -7.2975
Max Act: 6.7975. Min Act: -0.1700
Data Index: 43623 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2975. Min Range: -7.2975
Max Act: 6.7975. Min Act: -0.1700
Data Index: 38931 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2975. Min Range: -7.2975
Max Act: 6.7662. Min Act: -0.1700
Data Index: 4672263 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2975. Min Range: -7.2975
Max Act: 6.7662. Min Act: -0.1700
Data Index: 8215462 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2975. Min Range: -7.2975
Max Act: 6.7662. Min Act: -0.1700
Data Index: 2416861 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2975. Min Range: -7.2975
Max Act: 6.7662. Min Act: -0.1700
Data Index: 3222485 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2975. Min Range: -7.2975
Max Act: 6.7350. Min Act: -0.1700
Data Index: 2578199 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2975. Min Range: -7.2975
Max Act: 6.6725. Min Act: -0.1700
Data Index: 1030904 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #19