Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3828 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.8924. Min Range: -8.8924
Max Act: 8.8924. Min Act: -0.1700
Data Index: 231245 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.8924. Min Range: -8.8924
Max Act: 8.7674. Min Act: -0.1700
Data Index: 5134554 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.8924. Min Range: -8.8924
Max Act: 8.5799. Min Act: -0.1700
Data Index: 5952218 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.8924. Min Range: -8.8924
Max Act: 8.5799. Min Act: -0.1700
Data Index: 7925695 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.8924. Min Range: -8.8924
Max Act: 8.5799. Min Act: -0.1700
Data Index: 5442089 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.8924. Min Range: -8.8924
Max Act: 8.5174. Min Act: -0.1700
Data Index: 4420364 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.8924. Min Range: -8.8924
Max Act: 8.5174. Min Act: -0.1700
Data Index: 1591833 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.8924. Min Range: -8.8924
Max Act: 8.4549. Min Act: -0.1700
Data Index: 341165 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.8924. Min Range: -8.8924
Max Act: 8.4549. Min Act: -0.1700
Data Index: 1877834 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.8924. Min Range: -8.8924
Max Act: 8.3924. Min Act: -0.1700
Data Index: 3735349 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.8924. Min Range: -8.8924
Max Act: 8.3299. Min Act: -0.1700
Data Index: 5097227 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.8924. Min Range: -8.8924
Max Act: 8.2674. Min Act: -0.1700
Data Index: 3033822 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.8924. Min Range: -8.8924
Max Act: 8.2674. Min Act: -0.1700
Data Index: 625111 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.8924. Min Range: -8.8924
Max Act: 8.2674. Min Act: -0.1700
Data Index: 6960460 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.8924. Min Range: -8.8924
Max Act: 8.2674. Min Act: -0.1700
Data Index: 8682259 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.8924. Min Range: -8.8924
Max Act: 8.2674. Min Act: -0.1700
Data Index: 3259937 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.8924. Min Range: -8.8924
Max Act: 8.2049. Min Act: -0.1700
Data Index: 4791821 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.8924. Min Range: -8.8924
Max Act: 8.1424. Min Act: -0.1700
Data Index: 2252776 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.8924. Min Range: -8.8924
Max Act: 8.1424. Min Act: -0.1700
Data Index: 2865731 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.8924. Min Range: -8.8924
Max Act: 8.1424. Min Act: -0.1700
Data Index: 4204875 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #19