Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3360 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1651. Min Range: -5.1651
Max Act: 5.1651. Min Act: -0.1700
Data Index: 1397038 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1651. Min Range: -5.1651
Max Act: 4.8838. Min Act: -0.1700
Data Index: 5714392 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1651. Min Range: -5.1651
Max Act: 4.8526. Min Act: -0.1700
Data Index: 1397040 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1651. Min Range: -5.1651
Max Act: 4.8526. Min Act: -0.1700
Data Index: 1397041 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1651. Min Range: -5.1651
Max Act: 4.8213. Min Act: -0.1700
Data Index: 2469974 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1651. Min Range: -5.1651
Max Act: 4.7276. Min Act: -0.1700
Data Index: 5714393 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1651. Min Range: -5.1651
Max Act: 4.7276. Min Act: -0.1700
Data Index: 1397042 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1651. Min Range: -5.1651
Max Act: 4.7276. Min Act: -0.1700
Data Index: 470121 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1651. Min Range: -5.1651
Max Act: 4.6963. Min Act: -0.1700
Data Index: 247379 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1651. Min Range: -5.1651
Max Act: 4.6651. Min Act: -0.1700
Data Index: 5801485 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1651. Min Range: -5.1651
Max Act: 4.6963. Min Act: -0.1700
Data Index: 1397039 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1651. Min Range: -5.1651
Max Act: 4.6963. Min Act: -0.1700
Data Index: 7805846 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1651. Min Range: -5.1651
Max Act: 4.6651. Min Act: -0.1700
Data Index: 1397043 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1651. Min Range: -5.1651
Max Act: 4.6338. Min Act: -0.1700
Data Index: 4521115 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1651. Min Range: -5.1651
Max Act: 4.6651. Min Act: -0.1700
Data Index: 3018399 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1651. Min Range: -5.1651
Max Act: 4.6338. Min Act: -0.1700
Data Index: 2575225 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1651. Min Range: -5.1651
Max Act: 4.6026. Min Act: -0.1700
Data Index: 291958 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1651. Min Range: -5.1651
Max Act: 4.6338. Min Act: -0.1700
Data Index: 1639956 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1651. Min Range: -5.1651
Max Act: 4.6026. Min Act: -0.1700
Data Index: 6584369 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1651. Min Range: -5.1651
Max Act: 4.6026. Min Act: -0.1700
Data Index: 7753299 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #19