Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 768 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.5910. Min Range: -5.5910
Max Act: 5.5910. Min Act: -0.1700
Data Index: 4283520 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5910. Min Range: -5.5910
Max Act: 5.5597. Min Act: -0.1700
Data Index: 1238302 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5910. Min Range: -5.5910
Max Act: 5.4972. Min Act: -0.1700
Data Index: 7687298 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5910. Min Range: -5.5910
Max Act: 5.4972. Min Act: -0.1700
Data Index: 3463039 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5910. Min Range: -5.5910
Max Act: 5.4660. Min Act: -0.1700
Data Index: 4702706 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5910. Min Range: -5.5910
Max Act: 5.4347. Min Act: -0.1700
Data Index: 3509560 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5910. Min Range: -5.5910
Max Act: 5.4660. Min Act: -0.1700
Data Index: 8630148 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5910. Min Range: -5.5910
Max Act: 5.4035. Min Act: -0.1700
Data Index: 4370286 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5910. Min Range: -5.5910
Max Act: 5.4035. Min Act: -0.1700
Data Index: 7280224 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5910. Min Range: -5.5910
Max Act: 5.4035. Min Act: -0.1700
Data Index: 420674 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5910. Min Range: -5.5910
Max Act: 5.3410. Min Act: -0.1700
Data Index: 3149926 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5910. Min Range: -5.5910
Max Act: 5.3410. Min Act: -0.1700
Data Index: 4109561 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5910. Min Range: -5.5910
Max Act: 5.3410. Min Act: -0.1700
Data Index: 4310516 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5910. Min Range: -5.5910
Max Act: 5.3410. Min Act: -0.1700
Data Index: 3645485 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5910. Min Range: -5.5910
Max Act: 5.3722. Min Act: -0.1700
Data Index: 8487936 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5910. Min Range: -5.5910
Max Act: 5.3722. Min Act: -0.1700
Data Index: 4877389 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5910. Min Range: -5.5910
Max Act: 5.3410. Min Act: -0.1700
Data Index: 353080 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5910. Min Range: -5.5910
Max Act: 5.3097. Min Act: -0.1700
Data Index: 6519316 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5910. Min Range: -5.5910
Max Act: 5.2785. Min Act: -0.1700
Data Index: 967815 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5910. Min Range: -5.5910
Max Act: 5.2785. Min Act: -0.1700
Data Index: 7462470 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #19