Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2182 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.3670. Min Range: -6.3670
Max Act: 6.3670. Min Act: -0.1700
Data Index: 884079 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3670. Min Range: -6.3670
Max Act: 6.3045. Min Act: -0.1700
Data Index: 3381784 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3670. Min Range: -6.3670
Max Act: 6.3670. Min Act: -0.1700
Data Index: 8269916 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3670. Min Range: -6.3670
Max Act: 6.2420. Min Act: -0.1700
Data Index: 5488960 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3670. Min Range: -6.3670
Max Act: 6.2108. Min Act: -0.1700
Data Index: 1653159 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3670. Min Range: -6.3670
Max Act: 6.1795. Min Act: -0.1700
Data Index: 7846261 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3670. Min Range: -6.3670
Max Act: 6.1483. Min Act: -0.1700
Data Index: 3566832 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3670. Min Range: -6.3670
Max Act: 6.1170. Min Act: -0.1700
Data Index: 3476359 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3670. Min Range: -6.3670
Max Act: 6.1170. Min Act: -0.1700
Data Index: 1294007 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3670. Min Range: -6.3670
Max Act: 6.1483. Min Act: -0.1700
Data Index: 7011860 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3670. Min Range: -6.3670
Max Act: 6.1170. Min Act: -0.1700
Data Index: 738347 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3670. Min Range: -6.3670
Max Act: 6.0858. Min Act: -0.1700
Data Index: 3407452 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3670. Min Range: -6.3670
Max Act: 6.0858. Min Act: -0.1700
Data Index: 7898212 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3670. Min Range: -6.3670
Max Act: 6.0545. Min Act: -0.1700
Data Index: 5666025 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3670. Min Range: -6.3670
Max Act: 6.0545. Min Act: -0.1700
Data Index: 2075544 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3670. Min Range: -6.3670
Max Act: 6.0233. Min Act: -0.1700
Data Index: 5398475 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3670. Min Range: -6.3670
Max Act: 6.0545. Min Act: -0.1700
Data Index: 4534388 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3670. Min Range: -6.3670
Max Act: 6.0233. Min Act: -0.1700
Data Index: 2724263 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3670. Min Range: -6.3670
Max Act: 6.0233. Min Act: -0.1700
Data Index: 5640679 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3670. Min Range: -6.3670
Max Act: 6.0233. Min Act: -0.1700
Data Index: 7941616 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #19