Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2703 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8070. Min Range: -6.8070
Max Act: 6.8070. Min Act: -0.1700
Data Index: 4428324 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8070. Min Range: -6.8070
Max Act: 6.5570. Min Act: -0.1700
Data Index: 5999566 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8070. Min Range: -6.8070
Max Act: 6.5257. Min Act: -0.1700
Data Index: 2828752 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8070. Min Range: -6.8070
Max Act: 6.4632. Min Act: -0.1700
Data Index: 2629902 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8070. Min Range: -6.8070
Max Act: 6.4632. Min Act: -0.1700
Data Index: 4607668 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8070. Min Range: -6.8070
Max Act: 6.4320. Min Act: -0.1700
Data Index: 1919386 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8070. Min Range: -6.8070
Max Act: 6.4007. Min Act: -0.1700
Data Index: 8251984 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8070. Min Range: -6.8070
Max Act: 6.4007. Min Act: -0.1700
Data Index: 3908242 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8070. Min Range: -6.8070
Max Act: 6.3695. Min Act: -0.1700
Data Index: 3093221 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8070. Min Range: -6.8070
Max Act: 6.3382. Min Act: -0.1700
Data Index: 8583728 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8070. Min Range: -6.8070
Max Act: 6.3695. Min Act: -0.1700
Data Index: 4541173 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8070. Min Range: -6.8070
Max Act: 6.3382. Min Act: -0.1700
Data Index: 2383620 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8070. Min Range: -6.8070
Max Act: 6.3382. Min Act: -0.1700
Data Index: 4889558 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8070. Min Range: -6.8070
Max Act: 6.3382. Min Act: -0.1700
Data Index: 2924578 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8070. Min Range: -6.8070
Max Act: 6.3070. Min Act: -0.1700
Data Index: 7628061 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8070. Min Range: -6.8070
Max Act: 6.3070. Min Act: -0.1700
Data Index: 4004097 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8070. Min Range: -6.8070
Max Act: 6.2757. Min Act: -0.1700
Data Index: 3666323 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8070. Min Range: -6.8070
Max Act: 6.3382. Min Act: -0.1700
Data Index: 3924734 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8070. Min Range: -6.8070
Max Act: 6.2757. Min Act: -0.1700
Data Index: 4276059 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8070. Min Range: -6.8070
Max Act: 6.3070. Min Act: -0.1700
Data Index: 1583087 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #19