Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3340 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3091. Min Range: -7.3091
Max Act: 7.3091. Min Act: -0.1700
Data Index: 2553506 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3091. Min Range: -7.3091
Max Act: 7.2778. Min Act: -0.1700
Data Index: 2251043 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3091. Min Range: -7.3091
Max Act: 7.1216. Min Act: -0.1700
Data Index: 7782894 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3091. Min Range: -7.3091
Max Act: 7.0903. Min Act: -0.1700
Data Index: 6696052 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3091. Min Range: -7.3091
Max Act: 7.0903. Min Act: -0.1700
Data Index: 4116531 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3091. Min Range: -7.3091
Max Act: 7.0591. Min Act: -0.1700
Data Index: 587822 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3091. Min Range: -7.3091
Max Act: 7.0278. Min Act: -0.1700
Data Index: 8373093 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3091. Min Range: -7.3091
Max Act: 6.9653. Min Act: -0.1700
Data Index: 5459456 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3091. Min Range: -7.3091
Max Act: 6.9653. Min Act: -0.1700
Data Index: 7403671 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3091. Min Range: -7.3091
Max Act: 6.9028. Min Act: -0.1700
Data Index: 4460253 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3091. Min Range: -7.3091
Max Act: 6.9653. Min Act: -0.1700
Data Index: 5275436 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3091. Min Range: -7.3091
Max Act: 6.9653. Min Act: -0.1700
Data Index: 3325991 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3091. Min Range: -7.3091
Max Act: 6.9341. Min Act: -0.1700
Data Index: 1189252 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3091. Min Range: -7.3091
Max Act: 6.9341. Min Act: -0.1700
Data Index: 2890629 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3091. Min Range: -7.3091
Max Act: 6.9341. Min Act: -0.1700
Data Index: 8824833 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3091. Min Range: -7.3091
Max Act: 6.9341. Min Act: -0.1700
Data Index: 5840988 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3091. Min Range: -7.3091
Max Act: 6.9028. Min Act: -0.1700
Data Index: 4842544 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3091. Min Range: -7.3091
Max Act: 6.9028. Min Act: -0.1700
Data Index: 4039013 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3091. Min Range: -7.3091
Max Act: 6.9028. Min Act: -0.1700
Data Index: 4557826 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3091. Min Range: -7.3091
Max Act: 6.9028. Min Act: -0.1700
Data Index: 7016392 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #19