Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 714 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7382. Min Range: -6.7382
Max Act: 6.7382. Min Act: -0.1700
Data Index: 6721226 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7382. Min Range: -6.7382
Max Act: 6.5195. Min Act: -0.1700
Data Index: 4663873 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7382. Min Range: -6.7382
Max Act: 6.3320. Min Act: -0.1700
Data Index: 4193219 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7382. Min Range: -6.7382
Max Act: 6.1445. Min Act: -0.1700
Data Index: 7750030 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7382. Min Range: -6.7382
Max Act: 6.1132. Min Act: -0.1700
Data Index: 4235429 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7382. Min Range: -6.7382
Max Act: 6.1445. Min Act: -0.1700
Data Index: 2899102 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7382. Min Range: -6.7382
Max Act: 6.0820. Min Act: -0.1700
Data Index: 2157913 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7382. Min Range: -6.7382
Max Act: 6.0820. Min Act: -0.1700
Data Index: 1326487 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7382. Min Range: -6.7382
Max Act: 6.1132. Min Act: -0.1700
Data Index: 1139847 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7382. Min Range: -6.7382
Max Act: 6.0507. Min Act: -0.1700
Data Index: 1420409 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7382. Min Range: -6.7382
Max Act: 6.0507. Min Act: -0.1700
Data Index: 7519878 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7382. Min Range: -6.7382
Max Act: 6.0195. Min Act: -0.1700
Data Index: 3956846 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7382. Min Range: -6.7382
Max Act: 6.0195. Min Act: -0.1700
Data Index: 3754340 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7382. Min Range: -6.7382
Max Act: 6.0195. Min Act: -0.1700
Data Index: 18056 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7382. Min Range: -6.7382
Max Act: 5.9882. Min Act: -0.1700
Data Index: 2395660 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7382. Min Range: -6.7382
Max Act: 5.9570. Min Act: -0.1700
Data Index: 2601917 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7382. Min Range: -6.7382
Max Act: 5.9570. Min Act: -0.1700
Data Index: 2528753 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7382. Min Range: -6.7382
Max Act: 5.9882. Min Act: -0.1700
Data Index: 3239162 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7382. Min Range: -6.7382
Max Act: 5.9257. Min Act: -0.1700
Data Index: 61964 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7382. Min Range: -6.7382
Max Act: 5.8945. Min Act: -0.1700
Data Index: 590128 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #19