Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1950 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7464. Min Range: -6.7464
Max Act: 6.7464. Min Act: -0.1700
Data Index: 8449877 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7464. Min Range: -6.7464
Max Act: 6.6839. Min Act: -0.1700
Data Index: 6461262 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7464. Min Range: -6.7464
Max Act: 6.5589. Min Act: -0.1700
Data Index: 7265261 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7464. Min Range: -6.7464
Max Act: 6.5589. Min Act: -0.1700
Data Index: 7386997 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7464. Min Range: -6.7464
Max Act: 6.5589. Min Act: -0.1700
Data Index: 1147428 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7464. Min Range: -6.7464
Max Act: 6.5277. Min Act: -0.1700
Data Index: 791573 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7464. Min Range: -6.7464
Max Act: 6.4964. Min Act: -0.1700
Data Index: 8388956 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7464. Min Range: -6.7464
Max Act: 6.5277. Min Act: -0.1700
Data Index: 6964227 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7464. Min Range: -6.7464
Max Act: 6.4964. Min Act: -0.1700
Data Index: 6131884 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7464. Min Range: -6.7464
Max Act: 6.4027. Min Act: -0.1700
Data Index: 3880038 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7464. Min Range: -6.7464
Max Act: 6.3714. Min Act: -0.1700
Data Index: 3945018 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7464. Min Range: -6.7464
Max Act: 6.3402. Min Act: -0.1700
Data Index: 944232 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7464. Min Range: -6.7464
Max Act: 6.3089. Min Act: -0.1700
Data Index: 2941817 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7464. Min Range: -6.7464
Max Act: 6.3089. Min Act: -0.1700
Data Index: 6267803 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7464. Min Range: -6.7464
Max Act: 6.3089. Min Act: -0.1700
Data Index: 4579848 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7464. Min Range: -6.7464
Max Act: 6.3089. Min Act: -0.1700
Data Index: 1358000 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7464. Min Range: -6.7464
Max Act: 6.2777. Min Act: -0.1700
Data Index: 1717801 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7464. Min Range: -6.7464
Max Act: 6.2777. Min Act: -0.1700
Data Index: 2784966 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7464. Min Range: -6.7464
Max Act: 6.2777. Min Act: -0.1700
Data Index: 7811560 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7464. Min Range: -6.7464
Max Act: 6.2464. Min Act: -0.1700
Data Index: 509405 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #19