Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3398 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.6463. Min Range: -5.6463
Max Act: 5.6463. Min Act: -0.1700
Data Index: 1026027 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6463. Min Range: -5.6463
Max Act: 5.5213. Min Act: -0.1700
Data Index: 8488567 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6463. Min Range: -5.6463
Max Act: 5.5525. Min Act: -0.1700
Data Index: 1141185 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6463. Min Range: -5.6463
Max Act: 5.3650. Min Act: -0.1700
Data Index: 2548438 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6463. Min Range: -5.6463
Max Act: 5.3338. Min Act: -0.1700
Data Index: 4629971 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6463. Min Range: -5.6463
Max Act: 5.3338. Min Act: -0.1700
Data Index: 7406219 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6463. Min Range: -5.6463
Max Act: 5.3338. Min Act: -0.1700
Data Index: 2643510 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6463. Min Range: -5.6463
Max Act: 5.3338. Min Act: -0.1700
Data Index: 4017508 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6463. Min Range: -5.6463
Max Act: 5.3025. Min Act: -0.1700
Data Index: 3961984 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6463. Min Range: -5.6463
Max Act: 5.2713. Min Act: -0.1700
Data Index: 6325906 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6463. Min Range: -5.6463
Max Act: 5.2088. Min Act: -0.1700
Data Index: 2846555 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6463. Min Range: -5.6463
Max Act: 5.2088. Min Act: -0.1700
Data Index: 1717085 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6463. Min Range: -5.6463
Max Act: 5.1775. Min Act: -0.1700
Data Index: 4719106 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6463. Min Range: -5.6463
Max Act: 5.1150. Min Act: -0.1700
Data Index: 8613587 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6463. Min Range: -5.6463
Max Act: 5.0838. Min Act: -0.1700
Data Index: 3008319 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6463. Min Range: -5.6463
Max Act: 5.0838. Min Act: -0.1700
Data Index: 8792377 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6463. Min Range: -5.6463
Max Act: 5.0525. Min Act: -0.1700
Data Index: 2398560 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6463. Min Range: -5.6463
Max Act: 5.0525. Min Act: -0.1700
Data Index: 6194681 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6463. Min Range: -5.6463
Max Act: 5.0838. Min Act: -0.1700
Data Index: 2671055 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6463. Min Range: -5.6463
Max Act: 5.0838. Min Act: -0.1700
Data Index: 8247761 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #19