Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4399 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6571. Min Range: -6.6571
Max Act: 6.6571. Min Act: -0.1700
Data Index: 7437039 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6571. Min Range: -6.6571
Max Act: 6.5321. Min Act: -0.1700
Data Index: 4270632 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6571. Min Range: -6.6571
Max Act: 6.4696. Min Act: -0.1700
Data Index: 4480938 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6571. Min Range: -6.6571
Max Act: 6.4384. Min Act: -0.1700
Data Index: 8199737 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6571. Min Range: -6.6571
Max Act: 6.2509. Min Act: -0.1700
Data Index: 5712261 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6571. Min Range: -6.6571
Max Act: 6.2509. Min Act: -0.1700
Data Index: 3035954 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6571. Min Range: -6.6571
Max Act: 6.2196. Min Act: -0.1700
Data Index: 4201145 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6571. Min Range: -6.6571
Max Act: 6.2196. Min Act: -0.1700
Data Index: 1980184 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6571. Min Range: -6.6571
Max Act: 6.2196. Min Act: -0.1700
Data Index: 8362603 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6571. Min Range: -6.6571
Max Act: 6.1571. Min Act: -0.1700
Data Index: 6555097 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6571. Min Range: -6.6571
Max Act: 6.1571. Min Act: -0.1700
Data Index: 8172686 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6571. Min Range: -6.6571
Max Act: 6.1884. Min Act: -0.1700
Data Index: 2394345 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6571. Min Range: -6.6571
Max Act: 6.1259. Min Act: -0.1700
Data Index: 3707593 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6571. Min Range: -6.6571
Max Act: 6.0946. Min Act: -0.1700
Data Index: 6168216 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6571. Min Range: -6.6571
Max Act: 6.0946. Min Act: -0.1700
Data Index: 5557439 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6571. Min Range: -6.6571
Max Act: 6.0634. Min Act: -0.1700
Data Index: 5598164 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6571. Min Range: -6.6571
Max Act: 6.0634. Min Act: -0.1700
Data Index: 147509 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6571. Min Range: -6.6571
Max Act: 6.0634. Min Act: -0.1700
Data Index: 3112662 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6571. Min Range: -6.6571
Max Act: 6.0634. Min Act: -0.1700
Data Index: 3511825 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6571. Min Range: -6.6571
Max Act: 6.0321. Min Act: -0.1700
Data Index: 4807267 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #19