Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3600 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3732. Min Range: -7.3732
Max Act: 7.3732. Min Act: -0.1700
Data Index: 28675 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3732. Min Range: -7.3732
Max Act: 7.3419. Min Act: -0.1700
Data Index: 4864704 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3732. Min Range: -7.3732
Max Act: 7.2482. Min Act: -0.1700
Data Index: 3193103 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3732. Min Range: -7.3732
Max Act: 7.1857. Min Act: -0.1700
Data Index: 47488 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3732. Min Range: -7.3732
Max Act: 7.1544. Min Act: -0.1700
Data Index: 5728983 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3732. Min Range: -7.3732
Max Act: 7.1232. Min Act: -0.1700
Data Index: 8128635 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3732. Min Range: -7.3732
Max Act: 7.0294. Min Act: -0.1700
Data Index: 3629411 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3732. Min Range: -7.3732
Max Act: 6.9982. Min Act: -0.1700
Data Index: 7556801 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3732. Min Range: -7.3732
Max Act: 6.9982. Min Act: -0.1700
Data Index: 7604325 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3732. Min Range: -7.3732
Max Act: 6.9669. Min Act: -0.1700
Data Index: 2927924 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3732. Min Range: -7.3732
Max Act: 6.9044. Min Act: -0.1700
Data Index: 5398295 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3732. Min Range: -7.3732
Max Act: 6.9357. Min Act: -0.1700
Data Index: 522810 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3732. Min Range: -7.3732
Max Act: 6.9357. Min Act: -0.1700
Data Index: 1980906 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3732. Min Range: -7.3732
Max Act: 6.9044. Min Act: -0.1700
Data Index: 5154521 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3732. Min Range: -7.3732
Max Act: 6.8732. Min Act: -0.1700
Data Index: 6486427 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3732. Min Range: -7.3732
Max Act: 6.8732. Min Act: -0.1700
Data Index: 1076932 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3732. Min Range: -7.3732
Max Act: 6.8419. Min Act: -0.1700
Data Index: 8626571 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3732. Min Range: -7.3732
Max Act: 6.8419. Min Act: -0.1700
Data Index: 7968615 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3732. Min Range: -7.3732
Max Act: 6.8419. Min Act: -0.1700
Data Index: 2384162 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3732. Min Range: -7.3732
Max Act: 6.8107. Min Act: -0.1700
Data Index: 8742826 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #19