Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3474 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6825. Min Range: -5.6825
Max Act: 5.6825. Min Act: -0.1700
Data Index: 1733019 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6825. Min Range: -5.6825
Max Act: 5.6825. Min Act: -0.1700
Data Index: 3609352 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6825. Min Range: -5.6825
Max Act: 5.6200. Min Act: -0.1700
Data Index: 543332 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6825. Min Range: -5.6825
Max Act: 5.6200. Min Act: -0.1700
Data Index: 5227804 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6825. Min Range: -5.6825
Max Act: 5.6200. Min Act: -0.1700
Data Index: 8313713 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6825. Min Range: -5.6825
Max Act: 5.5575. Min Act: -0.1700
Data Index: 7064928 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6825. Min Range: -5.6825
Max Act: 5.5575. Min Act: -0.1700
Data Index: 1393578 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6825. Min Range: -5.6825
Max Act: 5.5575. Min Act: -0.1700
Data Index: 6207868 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6825. Min Range: -5.6825
Max Act: 5.5262. Min Act: -0.1700
Data Index: 4515392 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6825. Min Range: -5.6825
Max Act: 5.4950. Min Act: -0.1700
Data Index: 820176 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6825. Min Range: -5.6825
Max Act: 5.4950. Min Act: -0.1700
Data Index: 6044092 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6825. Min Range: -5.6825
Max Act: 5.4950. Min Act: -0.1700
Data Index: 1400344 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6825. Min Range: -5.6825
Max Act: 5.4950. Min Act: -0.1700
Data Index: 4275143 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6825. Min Range: -5.6825
Max Act: 5.4637. Min Act: -0.1700
Data Index: 6389217 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6825. Min Range: -5.6825
Max Act: 5.4637. Min Act: -0.1700
Data Index: 3151024 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6825. Min Range: -5.6825
Max Act: 5.4637. Min Act: -0.1700
Data Index: 3553136 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6825. Min Range: -5.6825
Max Act: 5.4325. Min Act: -0.1700
Data Index: 5185451 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6825. Min Range: -5.6825
Max Act: 5.4325. Min Act: -0.1700
Data Index: 6509451 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6825. Min Range: -5.6825
Max Act: 5.4012. Min Act: -0.1700
Data Index: 3311327 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6825. Min Range: -5.6825
Max Act: 5.4325. Min Act: -0.1700
Data Index: 906062 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #19