Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 457 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2755. Min Range: -5.2755
Max Act: 5.2755. Min Act: -0.1700
Data Index: 4606733 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2755. Min Range: -5.2755
Max Act: 5.2755. Min Act: -0.1700
Data Index: 7775477 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2755. Min Range: -5.2755
Max Act: 5.2755. Min Act: -0.1700
Data Index: 6509659 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2755. Min Range: -5.2755
Max Act: 5.2442. Min Act: -0.1700
Data Index: 2971748 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2755. Min Range: -5.2755
Max Act: 5.1817. Min Act: -0.1700
Data Index: 4153557 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2755. Min Range: -5.2755
Max Act: 5.2130. Min Act: -0.1700
Data Index: 4652984 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2755. Min Range: -5.2755
Max Act: 5.1817. Min Act: -0.1700
Data Index: 1085767 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2755. Min Range: -5.2755
Max Act: 5.1505. Min Act: -0.1700
Data Index: 8784955 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2755. Min Range: -5.2755
Max Act: 5.1192. Min Act: -0.1700
Data Index: 4666910 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2755. Min Range: -5.2755
Max Act: 5.1192. Min Act: -0.1700
Data Index: 7755405 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2755. Min Range: -5.2755
Max Act: 5.0880. Min Act: -0.1700
Data Index: 4617617 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2755. Min Range: -5.2755
Max Act: 5.0567. Min Act: -0.1700
Data Index: 7244292 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2755. Min Range: -5.2755
Max Act: 5.0567. Min Act: -0.1700
Data Index: 2194676 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2755. Min Range: -5.2755
Max Act: 5.0567. Min Act: -0.1700
Data Index: 6696097 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2755. Min Range: -5.2755
Max Act: 5.0567. Min Act: -0.1700
Data Index: 6457659 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2755. Min Range: -5.2755
Max Act: 5.0567. Min Act: -0.1700
Data Index: 5037881 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2755. Min Range: -5.2755
Max Act: 5.0567. Min Act: -0.1700
Data Index: 4908111 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2755. Min Range: -5.2755
Max Act: 5.0255. Min Act: -0.1700
Data Index: 8257530 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2755. Min Range: -5.2755
Max Act: 4.9942. Min Act: -0.1700
Data Index: 1772057 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2755. Min Range: -5.2755
Max Act: 4.9942. Min Act: -0.1700
Data Index: 1653385 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #19