Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4082 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.5476. Min Range: -5.5476
Max Act: 5.5476. Min Act: -0.1700
Data Index: 5919637 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5476. Min Range: -5.5476
Max Act: 5.4539. Min Act: -0.1700
Data Index: 3631084 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5476. Min Range: -5.5476
Max Act: 5.3601. Min Act: -0.1700
Data Index: 3795767 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5476. Min Range: -5.5476
Max Act: 5.3601. Min Act: -0.1700
Data Index: 4273770 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5476. Min Range: -5.5476
Max Act: 5.2664. Min Act: -0.1700
Data Index: 5019762 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5476. Min Range: -5.5476
Max Act: 5.2351. Min Act: -0.1700
Data Index: 4114230 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5476. Min Range: -5.5476
Max Act: 5.2039. Min Act: -0.1700
Data Index: 981427 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5476. Min Range: -5.5476
Max Act: 5.2039. Min Act: -0.1700
Data Index: 3667551 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5476. Min Range: -5.5476
Max Act: 5.2039. Min Act: -0.1700
Data Index: 8543958 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5476. Min Range: -5.5476
Max Act: 5.2039. Min Act: -0.1700
Data Index: 8140270 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5476. Min Range: -5.5476
Max Act: 5.1726. Min Act: -0.1700
Data Index: 8154410 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5476. Min Range: -5.5476
Max Act: 5.1726. Min Act: -0.1700
Data Index: 5142475 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5476. Min Range: -5.5476
Max Act: 5.2039. Min Act: -0.1700
Data Index: 8347898 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5476. Min Range: -5.5476
Max Act: 5.1726. Min Act: -0.1700
Data Index: 1423825 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5476. Min Range: -5.5476
Max Act: 5.1726. Min Act: -0.1700
Data Index: 6728824 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5476. Min Range: -5.5476
Max Act: 5.1726. Min Act: -0.1700
Data Index: 1613506 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5476. Min Range: -5.5476
Max Act: 5.1414. Min Act: -0.1700
Data Index: 8170688 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5476. Min Range: -5.5476
Max Act: 5.1414. Min Act: -0.1700
Data Index: 3926130 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5476. Min Range: -5.5476
Max Act: 5.1414. Min Act: -0.1700
Data Index: 5616790 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5476. Min Range: -5.5476
Max Act: 5.1414. Min Act: -0.1700
Data Index: 8417448 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #19