Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4331 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.0294. Min Range: -9.0294
Max Act: 9.0294. Min Act: -0.1700
Data Index: 6317088 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.0294. Min Range: -9.0294
Max Act: 8.6544. Min Act: -0.1700
Data Index: 8126822 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.0294. Min Range: -9.0294
Max Act: 8.4669. Min Act: -0.1700
Data Index: 2331984 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.0294. Min Range: -9.0294
Max Act: 8.5294. Min Act: -0.1700
Data Index: 5758878 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.0294. Min Range: -9.0294
Max Act: 8.4669. Min Act: -0.1700
Data Index: 8126827 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.0294. Min Range: -9.0294
Max Act: 8.4044. Min Act: -0.1700
Data Index: 5530288 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.0294. Min Range: -9.0294
Max Act: 8.4044. Min Act: -0.1700
Data Index: 8126818 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.0294. Min Range: -9.0294
Max Act: 8.3419. Min Act: -0.1700
Data Index: 2712 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.0294. Min Range: -9.0294
Max Act: 8.4044. Min Act: -0.1700
Data Index: 1909236 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.0294. Min Range: -9.0294
Max Act: 8.3419. Min Act: -0.1700
Data Index: 2331980 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.0294. Min Range: -9.0294
Max Act: 8.2794. Min Act: -0.1700
Data Index: 2711 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.0294. Min Range: -9.0294
Max Act: 8.3419. Min Act: -0.1700
Data Index: 5530289 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.0294. Min Range: -9.0294
Max Act: 8.2794. Min Act: -0.1700
Data Index: 7861643 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.0294. Min Range: -9.0294
Max Act: 8.2794. Min Act: -0.1700
Data Index: 5355197 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.0294. Min Range: -9.0294
Max Act: 8.2794. Min Act: -0.1700
Data Index: 6317089 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.0294. Min Range: -9.0294
Max Act: 8.2794. Min Act: -0.1700
Data Index: 6330193 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.0294. Min Range: -9.0294
Max Act: 8.2169. Min Act: -0.1700
Data Index: 6330189 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.0294. Min Range: -9.0294
Max Act: 8.2169. Min Act: -0.1700
Data Index: 4833189 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.0294. Min Range: -9.0294
Max Act: 8.2169. Min Act: -0.1700
Data Index: 4833191 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.0294. Min Range: -9.0294
Max Act: 8.2169. Min Act: -0.1700
Data Index: 4833190 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #19