Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5043 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.3855. Min Range: -3.3855
Max Act: 3.3855. Min Act: -0.1700
Data Index: 6927779 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3855. Min Range: -3.3855
Max Act: 3.3855. Min Act: -0.1700
Data Index: 7090991 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3855. Min Range: -3.3855
Max Act: 3.3855. Min Act: -0.1700
Data Index: 6638370 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3855. Min Range: -3.3855
Max Act: 3.3855. Min Act: -0.1700
Data Index: 8122958 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3855. Min Range: -3.3855
Max Act: 3.3855. Min Act: -0.1700
Data Index: 8727208 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3855. Min Range: -3.3855
Max Act: 3.3855. Min Act: -0.1700
Data Index: 126863 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3855. Min Range: -3.3855
Max Act: 3.3855. Min Act: -0.1700
Data Index: 6512165 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3855. Min Range: -3.3855
Max Act: 3.3855. Min Act: -0.1700
Data Index: 4285688 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3855. Min Range: -3.3855
Max Act: 3.3855. Min Act: -0.1700
Data Index: 3134070 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3855. Min Range: -3.3855
Max Act: 3.3698. Min Act: -0.1700
Data Index: 4687620 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3855. Min Range: -3.3855
Max Act: 3.3541. Min Act: -0.1700
Data Index: 1561892 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3855. Min Range: -3.3855
Max Act: 3.3541. Min Act: -0.1700
Data Index: 7400423 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3855. Min Range: -3.3855
Max Act: 3.3541. Min Act: -0.1700
Data Index: 5197996 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3855. Min Range: -3.3855
Max Act: 3.3384. Min Act: -0.1700
Data Index: 214541 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3855. Min Range: -3.3855
Max Act: 3.3228. Min Act: -0.1700
Data Index: 1793738 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3855. Min Range: -3.3855
Max Act: 3.3228. Min Act: -0.1700
Data Index: 4403341 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3855. Min Range: -3.3855
Max Act: 3.3228. Min Act: -0.1700
Data Index: 1851379 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3855. Min Range: -3.3855
Max Act: 3.3228. Min Act: -0.1700
Data Index: 1277887 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3855. Min Range: -3.3855
Max Act: 3.3228. Min Act: -0.1700
Data Index: 2929818 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3855. Min Range: -3.3855
Max Act: 3.3228. Min Act: -0.1700
Data Index: 3875758 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19