Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1794 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.7123. Min Range: -8.7123
Max Act: 8.7123. Min Act: -0.1700
Data Index: 272744 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7123. Min Range: -8.7123
Max Act: 8.5248. Min Act: -0.1700
Data Index: 997691 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7123. Min Range: -8.7123
Max Act: 8.4623. Min Act: -0.1700
Data Index: 3328971 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7123. Min Range: -8.7123
Max Act: 8.3373. Min Act: -0.1700
Data Index: 6810476 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7123. Min Range: -8.7123
Max Act: 8.3373. Min Act: -0.1700
Data Index: 135192 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7123. Min Range: -8.7123
Max Act: 8.3373. Min Act: -0.1700
Data Index: 5000748 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7123. Min Range: -8.7123
Max Act: 8.2748. Min Act: -0.1700
Data Index: 2790632 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7123. Min Range: -8.7123
Max Act: 8.2748. Min Act: -0.1700
Data Index: 3914798 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7123. Min Range: -8.7123
Max Act: 8.2748. Min Act: -0.1700
Data Index: 7684139 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7123. Min Range: -8.7123
Max Act: 8.2748. Min Act: -0.1700
Data Index: 4815618 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7123. Min Range: -8.7123
Max Act: 8.2435. Min Act: -0.1700
Data Index: 1263258 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7123. Min Range: -8.7123
Max Act: 8.1810. Min Act: -0.1700
Data Index: 8256309 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7123. Min Range: -8.7123
Max Act: 8.1498. Min Act: -0.1700
Data Index: 5199827 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7123. Min Range: -8.7123
Max Act: 8.1498. Min Act: -0.1700
Data Index: 1679146 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7123. Min Range: -8.7123
Max Act: 8.2123. Min Act: -0.1700
Data Index: 7852121 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7123. Min Range: -8.7123
Max Act: 8.1498. Min Act: -0.1700
Data Index: 2290759 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7123. Min Range: -8.7123
Max Act: 8.1498. Min Act: -0.1700
Data Index: 3266092 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7123. Min Range: -8.7123
Max Act: 8.1498. Min Act: -0.1700
Data Index: 5303820 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7123. Min Range: -8.7123
Max Act: 8.1185. Min Act: -0.1700
Data Index: 698081 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7123. Min Range: -8.7123
Max Act: 8.1498. Min Act: -0.1700
Data Index: 6661215 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #19