Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4059 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6398. Min Range: -7.6398
Max Act: 7.6398. Min Act: -0.1700
Data Index: 4828091 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6398. Min Range: -7.6398
Max Act: 7.3585. Min Act: -0.1700
Data Index: 2450364 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6398. Min Range: -7.6398
Max Act: 7.3273. Min Act: -0.1700
Data Index: 1690530 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6398. Min Range: -7.6398
Max Act: 7.3273. Min Act: -0.1700
Data Index: 3849713 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6398. Min Range: -7.6398
Max Act: 7.2023. Min Act: -0.1700
Data Index: 4780309 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6398. Min Range: -7.6398
Max Act: 7.2023. Min Act: -0.1700
Data Index: 2700407 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6398. Min Range: -7.6398
Max Act: 7.2023. Min Act: -0.1700
Data Index: 2720269 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6398. Min Range: -7.6398
Max Act: 7.1398. Min Act: -0.1700
Data Index: 1020414 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6398. Min Range: -7.6398
Max Act: 7.1398. Min Act: -0.1700
Data Index: 4948657 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6398. Min Range: -7.6398
Max Act: 7.1085. Min Act: -0.1700
Data Index: 5934464 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6398. Min Range: -7.6398
Max Act: 7.1085. Min Act: -0.1700
Data Index: 8123496 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6398. Min Range: -7.6398
Max Act: 7.0773. Min Act: -0.1700
Data Index: 419379 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6398. Min Range: -7.6398
Max Act: 7.0460. Min Act: -0.1700
Data Index: 5910077 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6398. Min Range: -7.6398
Max Act: 7.0148. Min Act: -0.1700
Data Index: 5667834 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6398. Min Range: -7.6398
Max Act: 6.9523. Min Act: -0.1700
Data Index: 8450370 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6398. Min Range: -7.6398
Max Act: 6.9523. Min Act: -0.1700
Data Index: 3110822 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6398. Min Range: -7.6398
Max Act: 6.9523. Min Act: -0.1700
Data Index: 6319395 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6398. Min Range: -7.6398
Max Act: 6.8898. Min Act: -0.1700
Data Index: 5635171 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6398. Min Range: -7.6398
Max Act: 6.9210. Min Act: -0.1700
Data Index: 1182242 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6398. Min Range: -7.6398
Max Act: 6.9210. Min Act: -0.1700
Data Index: 115016 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #19