Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5353 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3152. Min Range: -5.3152
Max Act: 5.3152. Min Act: -0.1700
Data Index: 4613236 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3152. Min Range: -5.3152
Max Act: 5.1590. Min Act: -0.1700
Data Index: 2541150 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3152. Min Range: -5.3152
Max Act: 5.1590. Min Act: -0.1700
Data Index: 7930609 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3152. Min Range: -5.3152
Max Act: 5.0965. Min Act: -0.1700
Data Index: 5755083 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3152. Min Range: -5.3152
Max Act: 5.0027. Min Act: -0.1700
Data Index: 168749 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3152. Min Range: -5.3152
Max Act: 5.0027. Min Act: -0.1700
Data Index: 7750309 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3152. Min Range: -5.3152
Max Act: 4.9715. Min Act: -0.1700
Data Index: 7118778 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3152. Min Range: -5.3152
Max Act: 4.9715. Min Act: -0.1700
Data Index: 585771 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3152. Min Range: -5.3152
Max Act: 4.9715. Min Act: -0.1700
Data Index: 48412 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3152. Min Range: -5.3152
Max Act: 4.9715. Min Act: -0.1700
Data Index: 5159920 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3152. Min Range: -5.3152
Max Act: 4.9402. Min Act: -0.1700
Data Index: 3636609 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3152. Min Range: -5.3152
Max Act: 4.9402. Min Act: -0.1700
Data Index: 3907581 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3152. Min Range: -5.3152
Max Act: 4.9402. Min Act: -0.1700
Data Index: 7460620 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3152. Min Range: -5.3152
Max Act: 4.9402. Min Act: -0.1700
Data Index: 3550695 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3152. Min Range: -5.3152
Max Act: 4.9402. Min Act: -0.1700
Data Index: 5935279 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3152. Min Range: -5.3152
Max Act: 4.9402. Min Act: -0.1700
Data Index: 8392150 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3152. Min Range: -5.3152
Max Act: 4.9090. Min Act: -0.1700
Data Index: 7190441 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3152. Min Range: -5.3152
Max Act: 4.9090. Min Act: -0.1700
Data Index: 7460619 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3152. Min Range: -5.3152
Max Act: 4.9090. Min Act: -0.1700
Data Index: 4665943 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3152. Min Range: -5.3152
Max Act: 4.9090. Min Act: -0.1700
Data Index: 1065137 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #19