Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1721 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6360. Min Range: -7.6360
Max Act: 7.6360. Min Act: -0.1700
Data Index: 2562842 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6360. Min Range: -7.6360
Max Act: 7.6360. Min Act: -0.1700
Data Index: 4530202 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6360. Min Range: -7.6360
Max Act: 7.6048. Min Act: -0.1700
Data Index: 4977867 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6360. Min Range: -7.6360
Max Act: 7.4798. Min Act: -0.1700
Data Index: 3031400 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6360. Min Range: -7.6360
Max Act: 7.4485. Min Act: -0.1700
Data Index: 2230814 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6360. Min Range: -7.6360
Max Act: 7.3860. Min Act: -0.1700
Data Index: 417153 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6360. Min Range: -7.6360
Max Act: 7.3860. Min Act: -0.1700
Data Index: 8606263 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6360. Min Range: -7.6360
Max Act: 7.2923. Min Act: -0.1700
Data Index: 1717544 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6360. Min Range: -7.6360
Max Act: 7.2923. Min Act: -0.1700
Data Index: 2126695 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6360. Min Range: -7.6360
Max Act: 7.2610. Min Act: -0.1700
Data Index: 7686598 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6360. Min Range: -7.6360
Max Act: 7.2298. Min Act: -0.1700
Data Index: 100513 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6360. Min Range: -7.6360
Max Act: 7.1360. Min Act: -0.1700
Data Index: 1866121 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6360. Min Range: -7.6360
Max Act: 7.1360. Min Act: -0.1700
Data Index: 4359937 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6360. Min Range: -7.6360
Max Act: 7.1360. Min Act: -0.1700
Data Index: 8148655 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6360. Min Range: -7.6360
Max Act: 7.1360. Min Act: -0.1700
Data Index: 2440803 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6360. Min Range: -7.6360
Max Act: 7.1360. Min Act: -0.1700
Data Index: 6058721 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6360. Min Range: -7.6360
Max Act: 7.1360. Min Act: -0.1700
Data Index: 2091353 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6360. Min Range: -7.6360
Max Act: 7.1360. Min Act: -0.1700
Data Index: 2976428 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6360. Min Range: -7.6360
Max Act: 7.1048. Min Act: -0.1700
Data Index: 8470204 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6360. Min Range: -7.6360
Max Act: 7.0735. Min Act: -0.1700
Data Index: 1127820 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #19