Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4257 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.2776. Min Range: -4.2776
Max Act: 4.2776. Min Act: -0.1700
Data Index: 5055939 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2776. Min Range: -4.2776
Max Act: 4.0901. Min Act: -0.1700
Data Index: 6838556 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2776. Min Range: -4.2776
Max Act: 4.0276. Min Act: -0.1700
Data Index: 1174244 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2776. Min Range: -4.2776
Max Act: 4.0276. Min Act: -0.1700
Data Index: 8530693 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2776. Min Range: -4.2776
Max Act: 4.0276. Min Act: -0.1700
Data Index: 4781706 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2776. Min Range: -4.2776
Max Act: 3.9494. Min Act: -0.1700
Data Index: 4017046 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2776. Min Range: -4.2776
Max Act: 3.9338. Min Act: -0.1700
Data Index: 4305298 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2776. Min Range: -4.2776
Max Act: 3.9494. Min Act: -0.1700
Data Index: 345454 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2776. Min Range: -4.2776
Max Act: 3.8400. Min Act: -0.1700
Data Index: 4113955 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2776. Min Range: -4.2776
Max Act: 3.8713. Min Act: -0.1700
Data Index: 685830 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2776. Min Range: -4.2776
Max Act: 3.8556. Min Act: -0.1700
Data Index: 7862843 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2776. Min Range: -4.2776
Max Act: 3.8556. Min Act: -0.1700
Data Index: 8504278 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2776. Min Range: -4.2776
Max Act: 3.8400. Min Act: -0.1700
Data Index: 3912874 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2776. Min Range: -4.2776
Max Act: 3.8400. Min Act: -0.1700
Data Index: 7851842 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2776. Min Range: -4.2776
Max Act: 3.8556. Min Act: -0.1700
Data Index: 93444 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2776. Min Range: -4.2776
Max Act: 3.8400. Min Act: -0.1700
Data Index: 4591836 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2776. Min Range: -4.2776
Max Act: 3.8400. Min Act: -0.1700
Data Index: 5767993 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2776. Min Range: -4.2776
Max Act: 3.8400. Min Act: -0.1700
Data Index: 544063 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2776. Min Range: -4.2776
Max Act: 3.7931. Min Act: -0.1700
Data Index: 6836941 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2776. Min Range: -4.2776
Max Act: 3.8243. Min Act: -0.1700
Data Index: 1457955 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #19