Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5612 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7820. Min Range: -5.7820
Max Act: 5.7820. Min Act: -0.1700
Data Index: 1623375 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7820. Min Range: -5.7820
Max Act: 5.6570. Min Act: -0.1700
Data Index: 5779238 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7820. Min Range: -5.7820
Max Act: 5.5632. Min Act: -0.1700
Data Index: 5248526 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7820. Min Range: -5.7820
Max Act: 5.5632. Min Act: -0.1700
Data Index: 3175449 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7820. Min Range: -5.7820
Max Act: 5.5320. Min Act: -0.1700
Data Index: 6897489 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7820. Min Range: -5.7820
Max Act: 5.5320. Min Act: -0.1700
Data Index: 6526509 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7820. Min Range: -5.7820
Max Act: 5.4695. Min Act: -0.1700
Data Index: 500582 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7820. Min Range: -5.7820
Max Act: 5.4695. Min Act: -0.1700
Data Index: 8515867 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7820. Min Range: -5.7820
Max Act: 5.4695. Min Act: -0.1700
Data Index: 5735643 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7820. Min Range: -5.7820
Max Act: 5.4382. Min Act: -0.1700
Data Index: 1520300 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7820. Min Range: -5.7820
Max Act: 5.4382. Min Act: -0.1700
Data Index: 377094 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7820. Min Range: -5.7820
Max Act: 5.4382. Min Act: -0.1700
Data Index: 8107992 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7820. Min Range: -5.7820
Max Act: 5.4070. Min Act: -0.1700
Data Index: 2721012 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7820. Min Range: -5.7820
Max Act: 5.4070. Min Act: -0.1700
Data Index: 221083 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7820. Min Range: -5.7820
Max Act: 5.3757. Min Act: -0.1700
Data Index: 135174 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7820. Min Range: -5.7820
Max Act: 5.3757. Min Act: -0.1700
Data Index: 6283910 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7820. Min Range: -5.7820
Max Act: 5.3757. Min Act: -0.1700
Data Index: 2610897 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7820. Min Range: -5.7820
Max Act: 5.3445. Min Act: -0.1700
Data Index: 968791 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7820. Min Range: -5.7820
Max Act: 5.3445. Min Act: -0.1700
Data Index: 4829074 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7820. Min Range: -5.7820
Max Act: 5.3132. Min Act: -0.1700
Data Index: 8306978 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #19