Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4272 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3480. Min Range: -7.3480
Max Act: 7.3480. Min Act: -0.1700
Data Index: 2070700 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3480. Min Range: -7.3480
Max Act: 7.2855. Min Act: -0.1700
Data Index: 2470883 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3480. Min Range: -7.3480
Max Act: 7.1605. Min Act: -0.1700
Data Index: 4247061 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3480. Min Range: -7.3480
Max Act: 7.1918. Min Act: -0.1700
Data Index: 7296570 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3480. Min Range: -7.3480
Max Act: 7.1605. Min Act: -0.1700
Data Index: 2108006 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3480. Min Range: -7.3480
Max Act: 7.0980. Min Act: -0.1700
Data Index: 4887766 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3480. Min Range: -7.3480
Max Act: 7.1293. Min Act: -0.1700
Data Index: 1253455 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3480. Min Range: -7.3480
Max Act: 7.0980. Min Act: -0.1700
Data Index: 1458431 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3480. Min Range: -7.3480
Max Act: 7.0980. Min Act: -0.1700
Data Index: 1852781 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3480. Min Range: -7.3480
Max Act: 7.0668. Min Act: -0.1700
Data Index: 407423 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3480. Min Range: -7.3480
Max Act: 7.0668. Min Act: -0.1700
Data Index: 3614153 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3480. Min Range: -7.3480
Max Act: 7.0355. Min Act: -0.1700
Data Index: 1275118 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3480. Min Range: -7.3480
Max Act: 7.0043. Min Act: -0.1700
Data Index: 1280844 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3480. Min Range: -7.3480
Max Act: 7.0355. Min Act: -0.1700
Data Index: 2070489 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3480. Min Range: -7.3480
Max Act: 7.0043. Min Act: -0.1700
Data Index: 5978499 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3480. Min Range: -7.3480
Max Act: 6.9730. Min Act: -0.1700
Data Index: 2064409 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3480. Min Range: -7.3480
Max Act: 6.9418. Min Act: -0.1700
Data Index: 5015640 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3480. Min Range: -7.3480
Max Act: 6.9418. Min Act: -0.1700
Data Index: 1665242 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3480. Min Range: -7.3480
Max Act: 6.9418. Min Act: -0.1700
Data Index: 4324875 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3480. Min Range: -7.3480
Max Act: 6.9418. Min Act: -0.1700
Data Index: 2070706 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #19