Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4439 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1264. Min Range: -7.1264
Max Act: 7.1264. Min Act: -0.1700
Data Index: 2997554 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1264. Min Range: -7.1264
Max Act: 7.0327. Min Act: -0.1700
Data Index: 2997555 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1264. Min Range: -7.1264
Max Act: 6.9389. Min Act: -0.1700
Data Index: 3063831 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1264. Min Range: -7.1264
Max Act: 6.8452. Min Act: -0.1700
Data Index: 3403089 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1264. Min Range: -7.1264
Max Act: 6.8764. Min Act: -0.1700
Data Index: 8344347 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1264. Min Range: -7.1264
Max Act: 6.8452. Min Act: -0.1700
Data Index: 4776575 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1264. Min Range: -7.1264
Max Act: 6.7827. Min Act: -0.1700
Data Index: 3074786 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1264. Min Range: -7.1264
Max Act: 6.6889. Min Act: -0.1700
Data Index: 7510341 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1264. Min Range: -7.1264
Max Act: 6.6889. Min Act: -0.1700
Data Index: 2047965 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1264. Min Range: -7.1264
Max Act: 6.6264. Min Act: -0.1700
Data Index: 5164032 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1264. Min Range: -7.1264
Max Act: 6.5952. Min Act: -0.1700
Data Index: 5962074 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1264. Min Range: -7.1264
Max Act: 6.5952. Min Act: -0.1700
Data Index: 609655 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1264. Min Range: -7.1264
Max Act: 6.5952. Min Act: -0.1700
Data Index: 6693165 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1264. Min Range: -7.1264
Max Act: 6.5952. Min Act: -0.1700
Data Index: 6419357 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1264. Min Range: -7.1264
Max Act: 6.5952. Min Act: -0.1700
Data Index: 4470276 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1264. Min Range: -7.1264
Max Act: 6.5639. Min Act: -0.1700
Data Index: 3412677 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1264. Min Range: -7.1264
Max Act: 6.5327. Min Act: -0.1700
Data Index: 8314695 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1264. Min Range: -7.1264
Max Act: 6.5327. Min Act: -0.1700
Data Index: 3469314 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1264. Min Range: -7.1264
Max Act: 6.5327. Min Act: -0.1700
Data Index: 3905197 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1264. Min Range: -7.1264
Max Act: 6.5327. Min Act: -0.1700
Data Index: 6770652 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #19