Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3547 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7881. Min Range: -6.7881
Max Act: 6.7881. Min Act: -0.1700
Data Index: 3745614 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7881. Min Range: -6.7881
Max Act: 6.7881. Min Act: -0.1700
Data Index: 4818554 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7881. Min Range: -6.7881
Max Act: 6.7256. Min Act: -0.1700
Data Index: 6681880 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7881. Min Range: -6.7881
Max Act: 6.6943. Min Act: -0.1700
Data Index: 7909746 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7881. Min Range: -6.7881
Max Act: 6.5068. Min Act: -0.1700
Data Index: 7108588 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7881. Min Range: -6.7881
Max Act: 6.4756. Min Act: -0.1700
Data Index: 3773552 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7881. Min Range: -6.7881
Max Act: 6.4443. Min Act: -0.1700
Data Index: 8265790 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7881. Min Range: -6.7881
Max Act: 6.4131. Min Act: -0.1700
Data Index: 7096978 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7881. Min Range: -6.7881
Max Act: 6.3506. Min Act: -0.1700
Data Index: 6631292 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7881. Min Range: -6.7881
Max Act: 6.3193. Min Act: -0.1700
Data Index: 828418 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7881. Min Range: -6.7881
Max Act: 6.2881. Min Act: -0.1700
Data Index: 2050498 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7881. Min Range: -6.7881
Max Act: 6.2881. Min Act: -0.1700
Data Index: 5749254 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7881. Min Range: -6.7881
Max Act: 6.2568. Min Act: -0.1700
Data Index: 5980502 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7881. Min Range: -6.7881
Max Act: 6.2568. Min Act: -0.1700
Data Index: 8076814 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7881. Min Range: -6.7881
Max Act: 6.2256. Min Act: -0.1700
Data Index: 4263297 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7881. Min Range: -6.7881
Max Act: 6.1943. Min Act: -0.1700
Data Index: 7865576 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7881. Min Range: -6.7881
Max Act: 6.2256. Min Act: -0.1700
Data Index: 6200738 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7881. Min Range: -6.7881
Max Act: 6.1943. Min Act: -0.1700
Data Index: 7203176 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7881. Min Range: -6.7881
Max Act: 6.1943. Min Act: -0.1700
Data Index: 8234081 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7881. Min Range: -6.7881
Max Act: 6.1943. Min Act: -0.1700
Data Index: 3653567 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #19