Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1306 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8052. Min Range: -5.8052
Max Act: 5.8052. Min Act: -0.1700
Data Index: 671523 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8052. Min Range: -5.8052
Max Act: 5.6802. Min Act: -0.1700
Data Index: 5771935 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8052. Min Range: -5.8052
Max Act: 5.6802. Min Act: -0.1700
Data Index: 5542225 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8052. Min Range: -5.8052
Max Act: 5.6177. Min Act: -0.1700
Data Index: 5493310 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8052. Min Range: -5.8052
Max Act: 5.5552. Min Act: -0.1700
Data Index: 8108854 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8052. Min Range: -5.8052
Max Act: 5.4927. Min Act: -0.1700
Data Index: 4064928 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8052. Min Range: -5.8052
Max Act: 5.4615. Min Act: -0.1700
Data Index: 6007799 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8052. Min Range: -5.8052
Max Act: 5.4302. Min Act: -0.1700
Data Index: 1476739 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8052. Min Range: -5.8052
Max Act: 5.4302. Min Act: -0.1700
Data Index: 8510491 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8052. Min Range: -5.8052
Max Act: 5.3990. Min Act: -0.1700
Data Index: 5360956 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8052. Min Range: -5.8052
Max Act: 5.4302. Min Act: -0.1700
Data Index: 4550722 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8052. Min Range: -5.8052
Max Act: 5.3990. Min Act: -0.1700
Data Index: 4862068 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8052. Min Range: -5.8052
Max Act: 5.3677. Min Act: -0.1700
Data Index: 5031798 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8052. Min Range: -5.8052
Max Act: 5.3365. Min Act: -0.1700
Data Index: 4668949 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8052. Min Range: -5.8052
Max Act: 5.3365. Min Act: -0.1700
Data Index: 7682955 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8052. Min Range: -5.8052
Max Act: 5.3365. Min Act: -0.1700
Data Index: 3610875 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8052. Min Range: -5.8052
Max Act: 5.3052. Min Act: -0.1700
Data Index: 4107603 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8052. Min Range: -5.8052
Max Act: 5.3052. Min Act: -0.1700
Data Index: 1440440 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8052. Min Range: -5.8052
Max Act: 5.3052. Min Act: -0.1700
Data Index: 2267764 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8052. Min Range: -5.8052
Max Act: 5.2740. Min Act: -0.1700
Data Index: 6672693 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #19