Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2022 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.8784. Min Range: -4.8784
Max Act: 4.8784. Min Act: -0.1700
Data Index: 4247854 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8784. Min Range: -4.8784
Max Act: 4.7221. Min Act: -0.1700
Data Index: 2487726 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8784. Min Range: -4.8784
Max Act: 4.5659. Min Act: -0.1700
Data Index: 1735237 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8784. Min Range: -4.8784
Max Act: 4.5971. Min Act: -0.1700
Data Index: 5255495 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8784. Min Range: -4.8784
Max Act: 4.5659. Min Act: -0.1700
Data Index: 771237 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8784. Min Range: -4.8784
Max Act: 4.5034. Min Act: -0.1700
Data Index: 809595 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8784. Min Range: -4.8784
Max Act: 4.5346. Min Act: -0.1700
Data Index: 8391870 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8784. Min Range: -4.8784
Max Act: 4.5034. Min Act: -0.1700
Data Index: 2438541 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8784. Min Range: -4.8784
Max Act: 4.5034. Min Act: -0.1700
Data Index: 6259306 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8784. Min Range: -4.8784
Max Act: 4.5034. Min Act: -0.1700
Data Index: 1536237 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8784. Min Range: -4.8784
Max Act: 4.5034. Min Act: -0.1700
Data Index: 2520761 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8784. Min Range: -4.8784
Max Act: 4.5034. Min Act: -0.1700
Data Index: 3336126 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8784. Min Range: -4.8784
Max Act: 4.4721. Min Act: -0.1700
Data Index: 2528347 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8784. Min Range: -4.8784
Max Act: 4.4721. Min Act: -0.1700
Data Index: 3775015 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8784. Min Range: -4.8784
Max Act: 4.4721. Min Act: -0.1700
Data Index: 3759746 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8784. Min Range: -4.8784
Max Act: 4.4409. Min Act: -0.1700
Data Index: 1015877 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8784. Min Range: -4.8784
Max Act: 4.4409. Min Act: -0.1700
Data Index: 7799314 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8784. Min Range: -4.8784
Max Act: 4.4721. Min Act: -0.1700
Data Index: 2850237 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8784. Min Range: -4.8784
Max Act: 4.4409. Min Act: -0.1700
Data Index: 2756539 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8784. Min Range: -4.8784
Max Act: 4.4409. Min Act: -0.1700
Data Index: 5003609 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #19