Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2357 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1985. Min Range: -6.1985
Max Act: 6.1985. Min Act: -0.1700
Data Index: 3105228 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1985. Min Range: -6.1985
Max Act: 6.1360. Min Act: -0.1700
Data Index: 1061525 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1985. Min Range: -6.1985
Max Act: 5.9798. Min Act: -0.1700
Data Index: 858801 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1985. Min Range: -6.1985
Max Act: 5.7298. Min Act: -0.1700
Data Index: 5396024 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1985. Min Range: -6.1985
Max Act: 5.6985. Min Act: -0.1700
Data Index: 4861778 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1985. Min Range: -6.1985
Max Act: 5.6985. Min Act: -0.1700
Data Index: 199266 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1985. Min Range: -6.1985
Max Act: 5.6360. Min Act: -0.1700
Data Index: 414933 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1985. Min Range: -6.1985
Max Act: 5.6048. Min Act: -0.1700
Data Index: 8082260 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1985. Min Range: -6.1985
Max Act: 5.6048. Min Act: -0.1700
Data Index: 3239715 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1985. Min Range: -6.1985
Max Act: 5.5735. Min Act: -0.1700
Data Index: 4724172 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1985. Min Range: -6.1985
Max Act: 5.5423. Min Act: -0.1700
Data Index: 418525 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1985. Min Range: -6.1985
Max Act: 5.5423. Min Act: -0.1700
Data Index: 420787 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1985. Min Range: -6.1985
Max Act: 5.5423. Min Act: -0.1700
Data Index: 7097617 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1985. Min Range: -6.1985
Max Act: 5.4798. Min Act: -0.1700
Data Index: 6402456 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1985. Min Range: -6.1985
Max Act: 5.4485. Min Act: -0.1700
Data Index: 707696 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1985. Min Range: -6.1985
Max Act: 5.4485. Min Act: -0.1700
Data Index: 4396259 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1985. Min Range: -6.1985
Max Act: 5.4485. Min Act: -0.1700
Data Index: 3694092 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1985. Min Range: -6.1985
Max Act: 5.3860. Min Act: -0.1700
Data Index: 706396 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1985. Min Range: -6.1985
Max Act: 5.3860. Min Act: -0.1700
Data Index: 1125 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1985. Min Range: -6.1985
Max Act: 5.3860. Min Act: -0.1700
Data Index: 5291228 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #19