Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3337 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6674. Min Range: -5.6674
Max Act: 5.6674. Min Act: -0.1700
Data Index: 5568936 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6674. Min Range: -5.6674
Max Act: 5.6674. Min Act: -0.1700
Data Index: 2173259 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6674. Min Range: -5.6674
Max Act: 5.6674. Min Act: -0.1700
Data Index: 6902903 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6674. Min Range: -5.6674
Max Act: 5.6049. Min Act: -0.1700
Data Index: 5865207 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6674. Min Range: -5.6674
Max Act: 5.5424. Min Act: -0.1700
Data Index: 6149038 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6674. Min Range: -5.6674
Max Act: 5.5424. Min Act: -0.1700
Data Index: 7897340 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6674. Min Range: -5.6674
Max Act: 5.5112. Min Act: -0.1700
Data Index: 6902902 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6674. Min Range: -5.6674
Max Act: 5.4799. Min Act: -0.1700
Data Index: 7897338 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6674. Min Range: -5.6674
Max Act: 5.4799. Min Act: -0.1700
Data Index: 6902900 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6674. Min Range: -5.6674
Max Act: 5.4799. Min Act: -0.1700
Data Index: 3448415 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6674. Min Range: -5.6674
Max Act: 5.4487. Min Act: -0.1700
Data Index: 4402261 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6674. Min Range: -5.6674
Max Act: 5.4487. Min Act: -0.1700
Data Index: 6902905 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6674. Min Range: -5.6674
Max Act: 5.4174. Min Act: -0.1700
Data Index: 6902901 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6674. Min Range: -5.6674
Max Act: 5.3862. Min Act: -0.1700
Data Index: 5865209 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6674. Min Range: -5.6674
Max Act: 5.3862. Min Act: -0.1700
Data Index: 3408783 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6674. Min Range: -5.6674
Max Act: 5.3862. Min Act: -0.1700
Data Index: 4539523 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6674. Min Range: -5.6674
Max Act: 5.3862. Min Act: -0.1700
Data Index: 7897342 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6674. Min Range: -5.6674
Max Act: 5.3549. Min Act: -0.1700
Data Index: 2005525 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6674. Min Range: -5.6674
Max Act: 5.3237. Min Act: -0.1700
Data Index: 8536585 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6674. Min Range: -5.6674
Max Act: 5.3237. Min Act: -0.1700
Data Index: 3448414 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #19