Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2852 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8500. Min Range: -6.8500
Max Act: 6.8500. Min Act: -0.1700
Data Index: 5237551 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8500. Min Range: -6.8500
Max Act: 6.4125. Min Act: -0.1700
Data Index: 3115080 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8500. Min Range: -6.8500
Max Act: 6.3187. Min Act: -0.1700
Data Index: 4158135 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8500. Min Range: -6.8500
Max Act: 6.3187. Min Act: -0.1700
Data Index: 7636804 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8500. Min Range: -6.8500
Max Act: 6.2875. Min Act: -0.1700
Data Index: 1829680 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8500. Min Range: -6.8500
Max Act: 6.2875. Min Act: -0.1700
Data Index: 1072744 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8500. Min Range: -6.8500
Max Act: 6.1937. Min Act: -0.1700
Data Index: 6334590 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8500. Min Range: -6.8500
Max Act: 6.1625. Min Act: -0.1700
Data Index: 4148446 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8500. Min Range: -6.8500
Max Act: 6.1937. Min Act: -0.1700
Data Index: 957093 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8500. Min Range: -6.8500
Max Act: 6.1937. Min Act: -0.1700
Data Index: 6228640 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8500. Min Range: -6.8500
Max Act: 6.1312. Min Act: -0.1700
Data Index: 8059140 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8500. Min Range: -6.8500
Max Act: 6.1312. Min Act: -0.1700
Data Index: 1642280 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8500. Min Range: -6.8500
Max Act: 6.1000. Min Act: -0.1700
Data Index: 1751328 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8500. Min Range: -6.8500
Max Act: 6.0687. Min Act: -0.1700
Data Index: 721303 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8500. Min Range: -6.8500
Max Act: 6.0375. Min Act: -0.1700
Data Index: 673471 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8500. Min Range: -6.8500
Max Act: 6.0375. Min Act: -0.1700
Data Index: 2216534 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8500. Min Range: -6.8500
Max Act: 6.0062. Min Act: -0.1700
Data Index: 4747316 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8500. Min Range: -6.8500
Max Act: 6.0062. Min Act: -0.1700
Data Index: 3435675 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8500. Min Range: -6.8500
Max Act: 6.0062. Min Act: -0.1700
Data Index: 2973332 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8500. Min Range: -6.8500
Max Act: 6.0062. Min Act: -0.1700
Data Index: 4434431 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #19