Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3416 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2646. Min Range: -7.2646
Max Act: 7.2646. Min Act: -0.1700
Data Index: 2424242 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2646. Min Range: -7.2646
Max Act: 7.1396. Min Act: -0.1700
Data Index: 1282399 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2646. Min Range: -7.2646
Max Act: 6.9521. Min Act: -0.1700
Data Index: 4716545 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2646. Min Range: -7.2646
Max Act: 6.9208. Min Act: -0.1700
Data Index: 3053047 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2646. Min Range: -7.2646
Max Act: 6.8896. Min Act: -0.1700
Data Index: 3453496 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2646. Min Range: -7.2646
Max Act: 6.8583. Min Act: -0.1700
Data Index: 8036144 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2646. Min Range: -7.2646
Max Act: 6.8583. Min Act: -0.1700
Data Index: 112081 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2646. Min Range: -7.2646
Max Act: 6.7958. Min Act: -0.1700
Data Index: 8136369 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2646. Min Range: -7.2646
Max Act: 6.8271. Min Act: -0.1700
Data Index: 7189018 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2646. Min Range: -7.2646
Max Act: 6.7958. Min Act: -0.1700
Data Index: 5579017 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2646. Min Range: -7.2646
Max Act: 6.8271. Min Act: -0.1700
Data Index: 1837003 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2646. Min Range: -7.2646
Max Act: 6.8271. Min Act: -0.1700
Data Index: 3508289 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2646. Min Range: -7.2646
Max Act: 6.7958. Min Act: -0.1700
Data Index: 5230758 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2646. Min Range: -7.2646
Max Act: 6.7958. Min Act: -0.1700
Data Index: 4483084 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2646. Min Range: -7.2646
Max Act: 6.7646. Min Act: -0.1700
Data Index: 5095372 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2646. Min Range: -7.2646
Max Act: 6.7333. Min Act: -0.1700
Data Index: 3725747 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2646. Min Range: -7.2646
Max Act: 6.7021. Min Act: -0.1700
Data Index: 1385677 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2646. Min Range: -7.2646
Max Act: 6.7021. Min Act: -0.1700
Data Index: 5784712 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2646. Min Range: -7.2646
Max Act: 6.7021. Min Act: -0.1700
Data Index: 5178909 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2646. Min Range: -7.2646
Max Act: 6.7021. Min Act: -0.1700
Data Index: 7384332 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #19