Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3007 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.5665. Min Range: -10.5665
Max Act: 10.5665. Min Act: -0.1700
Data Index: 7376776 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.5665. Min Range: -10.5665
Max Act: 10.2540. Min Act: -0.1700
Data Index: 4787826 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.5665. Min Range: -10.5665
Max Act: 10.0665. Min Act: -0.1700
Data Index: 8580945 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.5665. Min Range: -10.5665
Max Act: 10.0665. Min Act: -0.1700
Data Index: 3862169 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.5665. Min Range: -10.5665
Max Act: 10.0665. Min Act: -0.1700
Data Index: 4633503 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.5665. Min Range: -10.5665
Max Act: 10.0040. Min Act: -0.1700
Data Index: 8320838 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.5665. Min Range: -10.5665
Max Act: 9.9415. Min Act: -0.1700
Data Index: 1110215 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.5665. Min Range: -10.5665
Max Act: 10.0665. Min Act: -0.1700
Data Index: 1087453 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.5665. Min Range: -10.5665
Max Act: 9.8165. Min Act: -0.1700
Data Index: 6390206 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.5665. Min Range: -10.5665
Max Act: 9.7540. Min Act: -0.1700
Data Index: 2594089 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.5665. Min Range: -10.5665
Max Act: 9.6915. Min Act: -0.1700
Data Index: 321119 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.5665. Min Range: -10.5665
Max Act: 9.6290. Min Act: -0.1700
Data Index: 6030452 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.5665. Min Range: -10.5665
Max Act: 9.6290. Min Act: -0.1700
Data Index: 8533736 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.5665. Min Range: -10.5665
Max Act: 9.6915. Min Act: -0.1700
Data Index: 935184 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.5665. Min Range: -10.5665
Max Act: 9.6290. Min Act: -0.1700
Data Index: 1429149 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.5665. Min Range: -10.5665
Max Act: 9.5665. Min Act: -0.1700
Data Index: 4003015 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.5665. Min Range: -10.5665
Max Act: 9.5665. Min Act: -0.1700
Data Index: 6051402 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.5665. Min Range: -10.5665
Max Act: 9.5040. Min Act: -0.1700
Data Index: 8044767 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.5665. Min Range: -10.5665
Max Act: 9.5665. Min Act: -0.1700
Data Index: 4300749 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.5665. Min Range: -10.5665
Max Act: 9.5665. Min Act: -0.1700
Data Index: 4922484 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #19