Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5397 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2411. Min Range: -6.2411
Max Act: 6.2411. Min Act: -0.1700
Data Index: 1836815 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2411. Min Range: -6.2411
Max Act: 6.0223. Min Act: -0.1700
Data Index: 1398562 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2411. Min Range: -6.2411
Max Act: 6.0223. Min Act: -0.1700
Data Index: 4471417 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2411. Min Range: -6.2411
Max Act: 5.9911. Min Act: -0.1700
Data Index: 3292304 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2411. Min Range: -6.2411
Max Act: 5.8973. Min Act: -0.1700
Data Index: 821856 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2411. Min Range: -6.2411
Max Act: 5.8661. Min Act: -0.1700
Data Index: 5247881 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2411. Min Range: -6.2411
Max Act: 5.8348. Min Act: -0.1700
Data Index: 6939977 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2411. Min Range: -6.2411
Max Act: 5.8348. Min Act: -0.1700
Data Index: 1259080 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2411. Min Range: -6.2411
Max Act: 5.8661. Min Act: -0.1700
Data Index: 474989 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2411. Min Range: -6.2411
Max Act: 5.8036. Min Act: -0.1700
Data Index: 5597869 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2411. Min Range: -6.2411
Max Act: 5.7723. Min Act: -0.1700
Data Index: 4263423 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2411. Min Range: -6.2411
Max Act: 5.7411. Min Act: -0.1700
Data Index: 5199058 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2411. Min Range: -6.2411
Max Act: 5.7411. Min Act: -0.1700
Data Index: 7379213 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2411. Min Range: -6.2411
Max Act: 5.7411. Min Act: -0.1700
Data Index: 7464769 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2411. Min Range: -6.2411
Max Act: 5.7098. Min Act: -0.1700
Data Index: 5225589 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2411. Min Range: -6.2411
Max Act: 5.7098. Min Act: -0.1700
Data Index: 7759051 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2411. Min Range: -6.2411
Max Act: 5.6473. Min Act: -0.1700
Data Index: 4611689 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2411. Min Range: -6.2411
Max Act: 5.6786. Min Act: -0.1700
Data Index: 4791829 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2411. Min Range: -6.2411
Max Act: 5.6786. Min Act: -0.1700
Data Index: 5306149 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2411. Min Range: -6.2411
Max Act: 5.6473. Min Act: -0.1700
Data Index: 2717807 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #19