Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5970 in Layer 41
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6788. Min Range: -7.6788
Max Act: 7.6788. Min Act: -0.1700
Data Index: 97383 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6788. Min Range: -7.6788
Max Act: 7.5850. Min Act: -0.1700
Data Index: 2473217 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6788. Min Range: -7.6788
Max Act: 7.6163. Min Act: -0.1700
Data Index: 1146152 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6788. Min Range: -7.6788
Max Act: 7.4913. Min Act: -0.1700
Data Index: 597557 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6788. Min Range: -7.6788
Max Act: 7.4913. Min Act: -0.1700
Data Index: 3769886 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6788. Min Range: -7.6788
Max Act: 7.4913. Min Act: -0.1700
Data Index: 7135919 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6788. Min Range: -7.6788
Max Act: 7.4600. Min Act: -0.1700
Data Index: 6706166 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6788. Min Range: -7.6788
Max Act: 7.4288. Min Act: -0.1700
Data Index: 2812936 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6788. Min Range: -7.6788
Max Act: 7.4288. Min Act: -0.1700
Data Index: 4237622 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6788. Min Range: -7.6788
Max Act: 7.3975. Min Act: -0.1700
Data Index: 7731851 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6788. Min Range: -7.6788
Max Act: 7.3663. Min Act: -0.1700
Data Index: 5447334 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6788. Min Range: -7.6788
Max Act: 7.3663. Min Act: -0.1700
Data Index: 4382315 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6788. Min Range: -7.6788
Max Act: 7.3350. Min Act: -0.1700
Data Index: 2023185 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6788. Min Range: -7.6788
Max Act: 7.3350. Min Act: -0.1700
Data Index: 2802819 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6788. Min Range: -7.6788
Max Act: 7.3350. Min Act: -0.1700
Data Index: 7220511 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6788. Min Range: -7.6788
Max Act: 7.3038. Min Act: -0.1700
Data Index: 3137266 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6788. Min Range: -7.6788
Max Act: 7.2725. Min Act: -0.1700
Data Index: 2747196 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6788. Min Range: -7.6788
Max Act: 7.2413. Min Act: -0.1700
Data Index: 3503881 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6788. Min Range: -7.6788
Max Act: 7.2413. Min Act: -0.1700
Data Index: 1885522 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6788. Min Range: -7.6788
Max Act: 7.1788. Min Act: -0.1700
Data Index: 4666217 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #19