Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3478 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8287. Min Range: -5.8287
Max Act: 5.8287. Min Act: -0.1700
Data Index: 7484455 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8287. Min Range: -5.8287
Max Act: 5.8287. Min Act: -0.1700
Data Index: 5707709 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8287. Min Range: -5.8287
Max Act: 5.7975. Min Act: -0.1700
Data Index: 4990866 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8287. Min Range: -5.8287
Max Act: 5.7662. Min Act: -0.1700
Data Index: 3686090 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8287. Min Range: -5.8287
Max Act: 5.7350. Min Act: -0.1700
Data Index: 744144 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8287. Min Range: -5.8287
Max Act: 5.7350. Min Act: -0.1700
Data Index: 6191727 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8287. Min Range: -5.8287
Max Act: 5.7350. Min Act: -0.1700
Data Index: 2122853 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8287. Min Range: -5.8287
Max Act: 5.7350. Min Act: -0.1700
Data Index: 8450389 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8287. Min Range: -5.8287
Max Act: 5.7662. Min Act: -0.1700
Data Index: 1941262 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8287. Min Range: -5.8287
Max Act: 5.7037. Min Act: -0.1700
Data Index: 3285640 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8287. Min Range: -5.8287
Max Act: 5.7037. Min Act: -0.1700
Data Index: 5263433 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8287. Min Range: -5.8287
Max Act: 5.7037. Min Act: -0.1700
Data Index: 5263526 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8287. Min Range: -5.8287
Max Act: 5.7037. Min Act: -0.1700
Data Index: 4673577 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8287. Min Range: -5.8287
Max Act: 5.7037. Min Act: -0.1700
Data Index: 2096503 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8287. Min Range: -5.8287
Max Act: 5.6725. Min Act: -0.1700
Data Index: 390693 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8287. Min Range: -5.8287
Max Act: 5.6725. Min Act: -0.1700
Data Index: 7863621 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8287. Min Range: -5.8287
Max Act: 5.6412. Min Act: -0.1700
Data Index: 152091 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8287. Min Range: -5.8287
Max Act: 5.6100. Min Act: -0.1700
Data Index: 4593285 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8287. Min Range: -5.8287
Max Act: 5.6100. Min Act: -0.1700
Data Index: 6490973 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8287. Min Range: -5.8287
Max Act: 5.6100. Min Act: -0.1700
Data Index: 3175591 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #19