Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3616 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6332. Min Range: -4.6332
Max Act: 4.6332. Min Act: -0.1700
Data Index: 8377117 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6332. Min Range: -4.6332
Max Act: 4.6332. Min Act: -0.1700
Data Index: 6587280 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6332. Min Range: -4.6332
Max Act: 4.6020. Min Act: -0.1700
Data Index: 2031159 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6332. Min Range: -4.6332
Max Act: 4.5707. Min Act: -0.1700
Data Index: 5160090 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6332. Min Range: -4.6332
Max Act: 4.5395. Min Act: -0.1700
Data Index: 8012876 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6332. Min Range: -4.6332
Max Act: 4.5395. Min Act: -0.1700
Data Index: 835874 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6332. Min Range: -4.6332
Max Act: 4.5082. Min Act: -0.1700
Data Index: 6867667 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6332. Min Range: -4.6332
Max Act: 4.5082. Min Act: -0.1700
Data Index: 3747828 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6332. Min Range: -4.6332
Max Act: 4.5082. Min Act: -0.1700
Data Index: 8214056 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6332. Min Range: -4.6332
Max Act: 4.5082. Min Act: -0.1700
Data Index: 548352 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6332. Min Range: -4.6332
Max Act: 4.4769. Min Act: -0.1700
Data Index: 3883871 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6332. Min Range: -4.6332
Max Act: 4.4769. Min Act: -0.1699
Data Index: 4663901 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6332. Min Range: -4.6332
Max Act: 4.4769. Min Act: -0.1700
Data Index: 1428259 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6332. Min Range: -4.6332
Max Act: 4.4769. Min Act: -0.1700
Data Index: 1129793 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6332. Min Range: -4.6332
Max Act: 4.4769. Min Act: -0.1700
Data Index: 6399901 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6332. Min Range: -4.6332
Max Act: 4.4457. Min Act: -0.1700
Data Index: 5161994 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6332. Min Range: -4.6332
Max Act: 4.4457. Min Act: -0.1700
Data Index: 46385 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6332. Min Range: -4.6332
Max Act: 4.4457. Min Act: -0.1700
Data Index: 5874670 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6332. Min Range: -4.6332
Max Act: 4.4457. Min Act: -0.1700
Data Index: 1504560 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6332. Min Range: -4.6332
Max Act: 4.4457. Min Act: -0.1700
Data Index: 225201 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #19