Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1446 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4999. Min Range: -6.4999
Max Act: 6.4999. Min Act: -0.1700
Data Index: 36059 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4999. Min Range: -6.4999
Max Act: 6.4374. Min Act: -0.1700
Data Index: 583687 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4999. Min Range: -6.4999
Max Act: 6.3436. Min Act: -0.1700
Data Index: 4164740 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4999. Min Range: -6.4999
Max Act: 6.3124. Min Act: -0.1700
Data Index: 822789 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4999. Min Range: -6.4999
Max Act: 6.3124. Min Act: -0.1700
Data Index: 4247937 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4999. Min Range: -6.4999
Max Act: 6.2499. Min Act: -0.1700
Data Index: 4090738 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4999. Min Range: -6.4999
Max Act: 6.2186. Min Act: -0.1700
Data Index: 6183355 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4999. Min Range: -6.4999
Max Act: 6.2186. Min Act: -0.1700
Data Index: 6682496 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4999. Min Range: -6.4999
Max Act: 6.2186. Min Act: -0.1700
Data Index: 7285710 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4999. Min Range: -6.4999
Max Act: 6.1874. Min Act: -0.1700
Data Index: 4259898 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4999. Min Range: -6.4999
Max Act: 6.1874. Min Act: -0.1700
Data Index: 5700065 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4999. Min Range: -6.4999
Max Act: 6.1874. Min Act: -0.1700
Data Index: 3742359 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4999. Min Range: -6.4999
Max Act: 6.1561. Min Act: -0.1700
Data Index: 6832166 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4999. Min Range: -6.4999
Max Act: 6.1561. Min Act: -0.1700
Data Index: 2310061 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4999. Min Range: -6.4999
Max Act: 6.1561. Min Act: -0.1700
Data Index: 453956 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4999. Min Range: -6.4999
Max Act: 6.1874. Min Act: -0.1700
Data Index: 7387008 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4999. Min Range: -6.4999
Max Act: 6.1561. Min Act: -0.1700
Data Index: 4983186 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4999. Min Range: -6.4999
Max Act: 6.1561. Min Act: -0.1700
Data Index: 3196308 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4999. Min Range: -6.4999
Max Act: 6.1249. Min Act: -0.1700
Data Index: 941919 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4999. Min Range: -6.4999
Max Act: 6.0936. Min Act: -0.1700
Data Index: 1864083 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #19