Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4434 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.7686. Min Range: -6.7686
Max Act: 6.7686. Min Act: -0.1700
Data Index: 757826 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7686. Min Range: -6.7686
Max Act: 6.6749. Min Act: -0.1700
Data Index: 117344 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7686. Min Range: -6.7686
Max Act: 6.5811. Min Act: -0.1700
Data Index: 4706191 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7686. Min Range: -6.7686
Max Act: 6.5499. Min Act: -0.1700
Data Index: 8461222 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7686. Min Range: -6.7686
Max Act: 6.3624. Min Act: -0.1700
Data Index: 2809724 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7686. Min Range: -6.7686
Max Act: 6.2999. Min Act: -0.1700
Data Index: 71220 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7686. Min Range: -6.7686
Max Act: 6.2686. Min Act: -0.1700
Data Index: 71608 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7686. Min Range: -6.7686
Max Act: 6.2686. Min Act: -0.1700
Data Index: 2912837 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7686. Min Range: -6.7686
Max Act: 6.2686. Min Act: -0.1700
Data Index: 1117729 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7686. Min Range: -6.7686
Max Act: 6.2686. Min Act: -0.1700
Data Index: 2776307 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7686. Min Range: -6.7686
Max Act: 6.2061. Min Act: -0.1700
Data Index: 897174 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7686. Min Range: -6.7686
Max Act: 6.2061. Min Act: -0.1700
Data Index: 1119183 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7686. Min Range: -6.7686
Max Act: 6.1749. Min Act: -0.1700
Data Index: 734833 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7686. Min Range: -6.7686
Max Act: 6.1749. Min Act: -0.1700
Data Index: 7485448 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7686. Min Range: -6.7686
Max Act: 6.1749. Min Act: -0.1700
Data Index: 7317061 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7686. Min Range: -6.7686
Max Act: 6.1436. Min Act: -0.1700
Data Index: 7951548 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7686. Min Range: -6.7686
Max Act: 6.1124. Min Act: -0.1700
Data Index: 5270000 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7686. Min Range: -6.7686
Max Act: 6.1124. Min Act: -0.1700
Data Index: 1295007 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7686. Min Range: -6.7686
Max Act: 6.1124. Min Act: -0.1700
Data Index: 3383442 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7686. Min Range: -6.7686
Max Act: 6.1124. Min Act: -0.1700
Data Index: 6903703 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #19