Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3644 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0860. Min Range: -8.0860
Max Act: 8.0860. Min Act: -0.1700
Data Index: 5878146 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0860. Min Range: -8.0860
Max Act: 7.9610. Min Act: -0.1700
Data Index: 1635298 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0860. Min Range: -8.0860
Max Act: 7.9297. Min Act: -0.1700
Data Index: 6610286 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0860. Min Range: -8.0860
Max Act: 7.8047. Min Act: -0.1700
Data Index: 205231 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0860. Min Range: -8.0860
Max Act: 7.7110. Min Act: -0.1700
Data Index: 5612432 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0860. Min Range: -8.0860
Max Act: 7.6797. Min Act: -0.1700
Data Index: 1636743 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0860. Min Range: -8.0860
Max Act: 7.6485. Min Act: -0.1700
Data Index: 3902709 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0860. Min Range: -8.0860
Max Act: 7.6485. Min Act: -0.1700
Data Index: 6629958 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0860. Min Range: -8.0860
Max Act: 7.6172. Min Act: -0.1700
Data Index: 696301 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0860. Min Range: -8.0860
Max Act: 7.5547. Min Act: -0.1700
Data Index: 403184 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0860. Min Range: -8.0860
Max Act: 7.5547. Min Act: -0.1700
Data Index: 6944392 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0860. Min Range: -8.0860
Max Act: 7.5547. Min Act: -0.1700
Data Index: 8099936 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0860. Min Range: -8.0860
Max Act: 7.5547. Min Act: -0.1700
Data Index: 2872690 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0860. Min Range: -8.0860
Max Act: 7.5547. Min Act: -0.1700
Data Index: 7542599 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0860. Min Range: -8.0860
Max Act: 7.5235. Min Act: -0.1700
Data Index: 8192856 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0860. Min Range: -8.0860
Max Act: 7.5235. Min Act: -0.1700
Data Index: 832614 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0860. Min Range: -8.0860
Max Act: 7.5235. Min Act: -0.1700
Data Index: 841325 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0860. Min Range: -8.0860
Max Act: 7.5235. Min Act: -0.1700
Data Index: 6237756 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0860. Min Range: -8.0860
Max Act: 7.4610. Min Act: -0.1700
Data Index: 5479502 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0860. Min Range: -8.0860
Max Act: 7.4610. Min Act: -0.1700
Data Index: 302650 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #19