Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2774 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0731. Min Range: -8.0731
Max Act: 8.0731. Min Act: -0.1700
Data Index: 257013 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0731. Min Range: -8.0731
Max Act: 8.0418. Min Act: -0.1700
Data Index: 2509797 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0731. Min Range: -8.0731
Max Act: 7.6981. Min Act: -0.1700
Data Index: 3640520 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0731. Min Range: -8.0731
Max Act: 7.6668. Min Act: -0.1700
Data Index: 2806295 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0731. Min Range: -8.0731
Max Act: 7.6356. Min Act: -0.1700
Data Index: 5215252 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0731. Min Range: -8.0731
Max Act: 7.6043. Min Act: -0.1700
Data Index: 5843060 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0731. Min Range: -8.0731
Max Act: 7.5731. Min Act: -0.1700
Data Index: 5509502 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0731. Min Range: -8.0731
Max Act: 7.5731. Min Act: -0.1700
Data Index: 2183233 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0731. Min Range: -8.0731
Max Act: 7.5731. Min Act: -0.1700
Data Index: 8425520 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0731. Min Range: -8.0731
Max Act: 7.4481. Min Act: -0.1700
Data Index: 5070740 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0731. Min Range: -8.0731
Max Act: 7.4793. Min Act: -0.1700
Data Index: 1230386 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0731. Min Range: -8.0731
Max Act: 7.4168. Min Act: -0.1700
Data Index: 1803933 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0731. Min Range: -8.0731
Max Act: 7.4168. Min Act: -0.1700
Data Index: 2279944 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0731. Min Range: -8.0731
Max Act: 7.4168. Min Act: -0.1700
Data Index: 3021491 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0731. Min Range: -8.0731
Max Act: 7.3856. Min Act: -0.1700
Data Index: 1440104 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0731. Min Range: -8.0731
Max Act: 7.3856. Min Act: -0.1700
Data Index: 6915544 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0731. Min Range: -8.0731
Max Act: 7.3543. Min Act: -0.1700
Data Index: 8416934 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0731. Min Range: -8.0731
Max Act: 7.3543. Min Act: -0.1700
Data Index: 3349407 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0731. Min Range: -8.0731
Max Act: 7.3543. Min Act: -0.1700
Data Index: 8393831 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0731. Min Range: -8.0731
Max Act: 7.3856. Min Act: -0.1700
Data Index: 1397437 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #19