Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4850 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.5770. Min Range: -2.5770
Max Act: 2.5770. Min Act: -0.1700
Data Index: 5816908 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5770. Min Range: -2.5770
Max Act: 2.4475. Min Act: -0.1700
Data Index: 4266461 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5770. Min Range: -2.5770
Max Act: 2.4475. Min Act: -0.1700
Data Index: 3238763 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5770. Min Range: -2.5770
Max Act: 2.4150. Min Act: -0.1700
Data Index: 7704111 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5770. Min Range: -2.5770
Max Act: 2.4150. Min Act: -0.1700
Data Index: 3238778 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5770. Min Range: -2.5770
Max Act: 2.4312. Min Act: -0.1700
Data Index: 5796916 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5770. Min Range: -2.5770
Max Act: 2.4150. Min Act: -0.1700
Data Index: 7198696 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5770. Min Range: -2.5770
Max Act: 2.3823. Min Act: -0.1700
Data Index: 2994934 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5770. Min Range: -2.5770
Max Act: 2.3660. Min Act: -0.1700
Data Index: 5471266 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5770. Min Range: -2.5770
Max Act: 2.3496. Min Act: -0.1700
Data Index: 7094826 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5770. Min Range: -2.5770
Max Act: 2.3168. Min Act: -0.1700
Data Index: 4266463 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5770. Min Range: -2.5770
Max Act: 2.3332. Min Act: -0.1700
Data Index: 1556356 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5770. Min Range: -2.5770
Max Act: 2.2012. Min Act: -0.1700
Data Index: 7638552 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5770. Min Range: -2.5770
Max Act: 2.2509. Min Act: -0.1700
Data Index: 7276694 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5770. Min Range: -2.5770
Max Act: 2.1846. Min Act: -0.1700
Data Index: 5816906 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5770. Min Range: -2.5770
Max Act: 2.2509. Min Act: -0.1700
Data Index: 2834028 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5770. Min Range: -2.5770
Max Act: 2.2839. Min Act: -0.1700
Data Index: 3238760 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5770. Min Range: -2.5770
Max Act: 2.2343. Min Act: -0.1700
Data Index: 935789 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5770. Min Range: -2.5770
Max Act: 2.2509. Min Act: -0.1700
Data Index: 149242 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5770. Min Range: -2.5770
Max Act: 2.2178. Min Act: -0.1700
Data Index: 4983392 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #19