Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3189 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.4695. Min Range: -9.4695
Max Act: 9.4695. Min Act: -0.1700
Data Index: 7494329 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.4695. Min Range: -9.4695
Max Act: 9.3445. Min Act: -0.1700
Data Index: 5315672 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.4695. Min Range: -9.4695
Max Act: 9.3445. Min Act: -0.1700
Data Index: 2214974 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.4695. Min Range: -9.4695
Max Act: 9.3445. Min Act: -0.1700
Data Index: 3600433 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.4695. Min Range: -9.4695
Max Act: 9.2820. Min Act: -0.1700
Data Index: 2275242 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.4695. Min Range: -9.4695
Max Act: 9.2195. Min Act: -0.1700
Data Index: 1876134 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.4695. Min Range: -9.4695
Max Act: 9.1570. Min Act: -0.1700
Data Index: 3071729 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.4695. Min Range: -9.4695
Max Act: 9.0945. Min Act: -0.1700
Data Index: 1160729 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.4695. Min Range: -9.4695
Max Act: 9.0945. Min Act: -0.1700
Data Index: 917900 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.4695. Min Range: -9.4695
Max Act: 9.0945. Min Act: -0.1700
Data Index: 2570350 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.4695. Min Range: -9.4695
Max Act: 9.0945. Min Act: -0.1700
Data Index: 1627522 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.4695. Min Range: -9.4695
Max Act: 9.0945. Min Act: -0.1700
Data Index: 6906261 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.4695. Min Range: -9.4695
Max Act: 9.0320. Min Act: -0.1700
Data Index: 4236289 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.4695. Min Range: -9.4695
Max Act: 8.9695. Min Act: -0.1700
Data Index: 1836073 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.4695. Min Range: -9.4695
Max Act: 8.9695. Min Act: -0.1700
Data Index: 3071728 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.4695. Min Range: -9.4695
Max Act: 8.9695. Min Act: -0.1700
Data Index: 1317178 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.4695. Min Range: -9.4695
Max Act: 8.9695. Min Act: -0.1700
Data Index: 5788876 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.4695. Min Range: -9.4695
Max Act: 8.9070. Min Act: -0.1700
Data Index: 2557673 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.4695. Min Range: -9.4695
Max Act: 8.9070. Min Act: -0.1700
Data Index: 8154845 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.4695. Min Range: -9.4695
Max Act: 8.8445. Min Act: -0.1700
Data Index: 2161113 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #19