Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2564 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.7116. Min Range: -6.7116
Max Act: 6.7116. Min Act: -0.1700
Data Index: 3147450 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7116. Min Range: -6.7116
Max Act: 6.6804. Min Act: -0.1700
Data Index: 4380322 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7116. Min Range: -6.7116
Max Act: 6.5241. Min Act: -0.1700
Data Index: 2662825 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7116. Min Range: -6.7116
Max Act: 6.4929. Min Act: -0.1700
Data Index: 5143824 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7116. Min Range: -6.7116
Max Act: 6.4304. Min Act: -0.1700
Data Index: 5576343 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7116. Min Range: -6.7116
Max Act: 6.4304. Min Act: -0.1700
Data Index: 8310130 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7116. Min Range: -6.7116
Max Act: 6.3991. Min Act: -0.1700
Data Index: 5977421 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7116. Min Range: -6.7116
Max Act: 6.3991. Min Act: -0.1700
Data Index: 4582859 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7116. Min Range: -6.7116
Max Act: 6.4304. Min Act: -0.1700
Data Index: 3953490 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7116. Min Range: -6.7116
Max Act: 6.2741. Min Act: -0.1700
Data Index: 6153828 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7116. Min Range: -6.7116
Max Act: 6.2741. Min Act: -0.1700
Data Index: 4407904 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7116. Min Range: -6.7116
Max Act: 6.3054. Min Act: -0.1700
Data Index: 1827520 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7116. Min Range: -6.7116
Max Act: 6.1804. Min Act: -0.1700
Data Index: 3873169 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7116. Min Range: -6.7116
Max Act: 6.1804. Min Act: -0.1700
Data Index: 7772218 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7116. Min Range: -6.7116
Max Act: 6.1491. Min Act: -0.1700
Data Index: 2382680 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7116. Min Range: -6.7116
Max Act: 6.1804. Min Act: -0.1700
Data Index: 7784716 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7116. Min Range: -6.7116
Max Act: 6.2116. Min Act: -0.1700
Data Index: 4630311 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7116. Min Range: -6.7116
Max Act: 6.2116. Min Act: -0.1700
Data Index: 8543314 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7116. Min Range: -6.7116
Max Act: 6.1179. Min Act: -0.1700
Data Index: 347876 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7116. Min Range: -6.7116
Max Act: 6.1491. Min Act: -0.1700
Data Index: 3686889 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #19