Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3405 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2381. Min Range: -8.2381
Max Act: 8.2381. Min Act: -0.1700
Data Index: 1757230 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2381. Min Range: -8.2381
Max Act: 8.1131. Min Act: -0.1700
Data Index: 6184871 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2381. Min Range: -8.2381
Max Act: 7.9256. Min Act: -0.1700
Data Index: 6666470 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2381. Min Range: -8.2381
Max Act: 7.9256. Min Act: -0.1700
Data Index: 3501005 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2381. Min Range: -8.2381
Max Act: 7.8631. Min Act: -0.1700
Data Index: 1460140 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2381. Min Range: -8.2381
Max Act: 7.8631. Min Act: -0.1700
Data Index: 2603212 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2381. Min Range: -8.2381
Max Act: 7.8006. Min Act: -0.1700
Data Index: 533643 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2381. Min Range: -8.2381
Max Act: 7.8006. Min Act: -0.1700
Data Index: 129964 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2381. Min Range: -8.2381
Max Act: 7.7068. Min Act: -0.1700
Data Index: 263500 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2381. Min Range: -8.2381
Max Act: 7.7381. Min Act: -0.1700
Data Index: 4576809 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2381. Min Range: -8.2381
Max Act: 7.7381. Min Act: -0.1700
Data Index: 5574991 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2381. Min Range: -8.2381
Max Act: 7.6756. Min Act: -0.1700
Data Index: 2292358 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2381. Min Range: -8.2381
Max Act: 7.6756. Min Act: -0.1700
Data Index: 2099419 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2381. Min Range: -8.2381
Max Act: 7.6756. Min Act: -0.1700
Data Index: 1752546 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2381. Min Range: -8.2381
Max Act: 7.6131. Min Act: -0.1700
Data Index: 3552422 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2381. Min Range: -8.2381
Max Act: 7.6131. Min Act: -0.1700
Data Index: 620010 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2381. Min Range: -8.2381
Max Act: 7.6131. Min Act: -0.1700
Data Index: 4463464 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2381. Min Range: -8.2381
Max Act: 7.6131. Min Act: -0.1700
Data Index: 1784678 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2381. Min Range: -8.2381
Max Act: 7.6131. Min Act: -0.1700
Data Index: 8696919 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2381. Min Range: -8.2381
Max Act: 7.5818. Min Act: -0.1700
Data Index: 7148729 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #19