Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4584 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.7686. Min Range: -4.7686
Max Act: 4.7686. Min Act: -0.1700
Data Index: 1975821 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7686. Min Range: -4.7686
Max Act: 4.4248. Min Act: -0.1700
Data Index: 5795008 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7686. Min Range: -4.7686
Max Act: 4.3623. Min Act: -0.1700
Data Index: 6758150 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7686. Min Range: -4.7686
Max Act: 4.2998. Min Act: -0.1700
Data Index: 998150 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7686. Min Range: -4.7686
Max Act: 4.2998. Min Act: -0.1700
Data Index: 8559742 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7686. Min Range: -4.7686
Max Act: 4.2373. Min Act: -0.1700
Data Index: 2821702 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7686. Min Range: -4.7686
Max Act: 4.2373. Min Act: -0.1700
Data Index: 5296813 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7686. Min Range: -4.7686
Max Act: 4.2373. Min Act: -0.1700
Data Index: 8324980 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7686. Min Range: -4.7686
Max Act: 4.2061. Min Act: -0.1700
Data Index: 998148 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7686. Min Range: -4.7686
Max Act: 4.1748. Min Act: -0.1700
Data Index: 6758154 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7686. Min Range: -4.7686
Max Act: 4.1748. Min Act: -0.1700
Data Index: 2310252 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7686. Min Range: -4.7686
Max Act: 4.1435. Min Act: -0.1700
Data Index: 7874025 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7686. Min Range: -4.7686
Max Act: 4.1123. Min Act: -0.1700
Data Index: 7765871 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7686. Min Range: -4.7686
Max Act: 4.0810. Min Act: -0.1700
Data Index: 2550540 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7686. Min Range: -4.7686
Max Act: 4.0498. Min Act: -0.1700
Data Index: 4316868 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7686. Min Range: -4.7686
Max Act: 4.0185. Min Act: -0.1700
Data Index: 1975814 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7686. Min Range: -4.7686
Max Act: 4.0498. Min Act: -0.1700
Data Index: 866920 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7686. Min Range: -4.7686
Max Act: 4.0810. Min Act: -0.1700
Data Index: 2658849 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7686. Min Range: -4.7686
Max Act: 4.0498. Min Act: -0.1700
Data Index: 2739161 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7686. Min Range: -4.7686
Max Act: 4.0498. Min Act: -0.1700
Data Index: 5424309 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #19